© 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. 27-TRANSCODER-HP
    7. 9708
    Prev
    Next
    INDEX
    Explanations

    ail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¤Ł
    -0.27
    pray
    -0.26
    nbr
    -0.25
    æ¤Ł
    -0.25
    çļĩåĨł
    -0.24
     folklore
    -0.24
     espect
    -0.24
    TOOLS
    -0.23
    çİ°è¡Į
    -0.23
     almond
    -0.23
    POSITIVE LOGITS
    /umd
    0.34
    asc
    0.28
    ึà¸ģ
    0.27
    -spin
    0.27
    主è§Ĥ
    0.27
     conf
    0.26
    _asc
    0.26
     asc
    0.26
    _mc
    0.26
     spin
    0.25
    Activations Density 0.012%

    No Known Activations