© 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. 130144
    Prev
    Next
    INDEX
    Explanations

    but

    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
     Fate
    -0.31
     additionally
    -0.26
    abay
    -0.25
    è°IJ
    -0.25
    è¿ĺè¦ģ
    -0.25
    æĭ¢
    -0.25
    watch
    -0.24
    har
    -0.24
    家åĽŃ
    -0.24
     watch
    -0.24
    POSITIVE LOGITS
    wind
    0.27
     winds
    0.27
    以åħį
    0.26
    Wind
    0.26
     wind
    0.26
     incentiv
    0.26
    ADA
    0.25
    ergy
    0.25
     Ðijез
    0.25
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    Activations Density 0.018%

    No Known Activations