© 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. 22-TRANSCODER-HP
    7. 112580
    Prev
    Next
    INDEX
    Explanations

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yal
    -0.28
    /flutter
    -0.25
     rtrim
    -0.24
    ving
    -0.24
    ç¥ŀè¯Ŀ
    -0.23
    ARRY
    -0.23
    åľ»
    -0.23
    oger
    -0.23
     eins
    -0.23
     testcase
    -0.23
    POSITIVE LOGITS
    rips
    0.27
     familiar
    0.27
    less
    0.27
     explicitly
    0.26
    side
    0.26
    ality
    0.25
    åįģå¹´åīį
    0.25
     phá
    0.25
    ãģ¥
    0.24
     difference
    0.24
    Activations Density 0.169%

    No Known Activations