© 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. 32-TRANSCODER-HP
    7. 43273
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.36
    ì²Ń
    -0.28
     _|
    -0.27
    è¡ĢèĦĤ
    -0.26
     upon
    -0.26
    _Entry
    -0.26
    tte
    -0.25
    åĽ´çĿĢ
    -0.24
    æĽ´æ·±
    -0.23
    isphere
    -0.23
    POSITIVE LOGITS
    ely
    0.33
    est
    0.33
    åľ°
    0.31
    elly
    0.31
    -to
    0.30
     tox
    0.30
    ly
    0.29
     to
    0.29
    å¾Ĺå¤ļ
    0.28
    EST
    0.28
    Activations Density 0.012%

    No Known Activations