© 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. 12-TRANSCODER-HP
    7. 23773
    Prev
    Next
    INDEX
    Explanations

    United Kingdom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaults
    -0.29
     Defaults
    -0.28
    oga
    -0.26
    åħįè´¹
    -0.26
     exhaust
    -0.25
    _Default
    -0.25
     bot
    -0.24
    ç¿Ģ
    -0.24
    defaults
    -0.24
    å®ŀåĬĽ
    -0.24
    POSITIVE LOGITS
    ldb
    0.27
    rab
    0.25
    éģı
    0.24
    ä¹Įåħĭ
    0.24
    olynomial
    0.24
    èĶ·
    0.24
    çł´ç¢İ
    0.23
     midfield
    0.23
     Nob
    0.23
    ç¢İçīĩ
    0.23
    Activations Density 0.007%

    No Known Activations