© 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. 14-TRANSCODER-HP
    7. 41195
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacks
    -0.28
     sacked
    -0.28
     Moved
    -0.28
    EEK
    -0.27
     StringWriter
    -0.27
     sack
    -0.26
    å½±
    -0.26
    -loader
    -0.25
    -faced
    -0.25
     roma
    -0.25
    POSITIVE LOGITS
    assign
    0.28
    ids
    0.28
     tips
    0.28
    é½IJ
    0.28
    zz
    0.28
    èĤ¢
    0.27
     tip
    0.26
    顶
    0.26
    (del
    0.26
     Cue
    0.26
    Activations Density 0.372%

    No Known Activations