© 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. 9814
    Prev
    Next
    INDEX
    Explanations

    coast

    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
     Gest
    -0.27
    åĴĮåıijå±ķ
    -0.26
    pst
    -0.25
    predictions
    -0.25
    _boxes
    -0.24
    æŁĦ
    -0.24
    toArray
    -0.23
    erializer
    -0.23
    å§Ĭ
    -0.23
    ä¸İåıijå±ķ
    -0.23
    POSITIVE LOGITS
    ing
    0.31
    ier
    0.31
     [["
    0.28
    setter
    0.28
    lands
    0.27
     rents
    0.27
    ulent
    0.27
    ives
    0.27
    lin
    0.26
    ient
    0.26
    Activations Density 0.002%

    No Known Activations