© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43851
    Prev
    Next
    INDEX
    Explanations

    Code and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æݸ
    -0.27
     partitions
    -0.25
    sWith
    -0.25
    个人è§ĤçĤ¹
    -0.24
     Retry
    -0.24
     terminals
    -0.24
    ////////////////////////////////////////////////////////////////////////////
    -0.24
     andra
    -0.24
    éĥ¨åī¯
    -0.24
     withd
    -0.23
    POSITIVE LOGITS
    èĢ³
    0.32
    day
    0.29
    PP
    0.29
    é¼ĵ
    0.28
    nar
    0.28
    DT
    0.27
    ling
    0.27
    agt
    0.26
     auto
    0.26
    ty
    0.26
    Activations Density 0.000%

    No Known Activations