© 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. 18-TRANSCODER-HP
    7. 89910
    Prev
    Next
    INDEX
    Explanations

    impact on people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elight
    -0.31
    è³ŀ
    -0.29
    raq
    -0.26
    æĿ¥è®²
    -0.26
    ("").
    -0.24
     grâce
    -0.24
    .dispatcher
    -0.24
     dziÄĻki
    -0.24
    èµı
    -0.24
     Mic
    -0.23
    POSITIVE LOGITS
    º«
    0.27
    åħ¬ç«ĭåĮ»éĻ¢
    0.25
     senior
    0.24
    KI
    0.24
    亲
    0.24
    深深çļĦ
    0.24
     replicated
    0.24
    hn
    0.24
    å®ŀè·µä¸Ń
    0.24
    åĬłéĩį
    0.23
    Activations Density 19.002%

    No Known Activations