© 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. 43960
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    Sequential
    -0.29
    eref
    -0.27
    icit
    -0.26
    meg
    -0.26
     BAS
    -0.26
    Band
    -0.25
    ÅĽnie
    -0.24
    'im
    -0.24
    æ³»
    -0.24
    æ´»
    -0.24
    POSITIVE LOGITS
     held
    0.29
    æĪİ
    0.28
    磶
    0.28
     наÑĢ
    0.27
    æĮģæľīçļĦ
    0.25
    èĤ¤
    0.25
    :key
    0.25
    æĢĢ
    0.24
    ADR
    0.24
    æĩ·
    0.24
    Activations Density 0.001%

    No Known Activations