© 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. 33-TRANSCODER-HP
    7. 53999
    Prev
    Next
    INDEX
    Explanations

    technical document text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.28
    FML
    -0.26
    ä»ĸ们æĺ¯
    -0.26
    çĪ¶åŃIJ
    -0.25
    structors
    -0.25
    äd
    -0.25
    vé
    -0.24
     Worlds
    -0.24
    pletion
    -0.24
    -Identifier
    -0.23
    POSITIVE LOGITS
     subs
    0.33
    arth
    0.32
     land
    0.30
     Br
    0.30
     quick
    0.28
    eling
    0.28
    BR
    0.27
    (undefined
    0.27
    Br
    0.27
    Sub
    0.27
    Activations Density 0.019%

    No Known Activations