© 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. 9394
    Prev
    Next
    INDEX
    Explanations

    quite

    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
    really
    -0.36
     really
    -0.33
    ç¡®å®ŀ
    -0.30
     indeed
    -0.28
     truly
    -0.28
     Really
    -0.28
     realmente
    -0.27
    éĿ¢åħ·
    -0.27
     REALLY
    -0.27
    羣æŃ£
    -0.26
    POSITIVE LOGITS
    èµ°äºĨ
    0.27
    keeper
    0.27
    LENGTH
    0.25
     identical
    0.25
     men
    0.24
    -men
    0.24
    utenberg
    0.24
    LOY
    0.24
    aways
    0.24
     nil
    0.23
    Activations Density 0.219%

    No Known Activations