© 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. 8183
    Prev
    Next
    INDEX
    Explanations

    .htaccess files

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Terms
    -0.41
     terms
    -0.39
     agree
    -0.33
    Terms
    -0.31
     kata
    -0.30
     agreement
    -0.30
    _terms
    -0.30
     TERMS
    -0.30
     agrees
    -0.29
     agreed
    -0.28
    POSITIVE LOGITS
    ampa
    0.29
    å¤ĸç±į
    0.29
    aders
    0.26
    izedName
    0.26
     PROCUREMENT
    0.26
    Apache
    0.25
    iture
    0.24
    ngth
    0.24
    Burn
    0.24
    pline
    0.23
    Activations Density 0.156%

    No Known Activations