© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    .fil
    -0.26
    arters
    -0.26
    side
    -0.24
     clearfix
    -0.24
    conds
    -0.24
    羣åĪĩ
    -0.24
    Ñıд
    -0.24
    ãĥĬãĥ¼
    -0.24
    figcaption
    -0.23
    ä¹ĭå¿ĥ
    -0.23
    POSITIVE LOGITS
    licit
    0.35
    _visibility
    0.29
    ãģłãģ¨æĢĿãģĨ
    0.26
    ç«ŀäºīåĬĽ
    0.26
    visibility
    0.26
    çģ¾
    0.26
    MOST
    0.25
     consistency
    0.25
    å®ŀè·µ
    0.25
     Cons
    0.25
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.