© 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. 19-TRANSCODER-HP
    7. 8175
    Prev
    Next
    INDEX
    Explanations

    mortality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı¶åŃIJ
    -0.28
    åĿŃ
    -0.27
    structors
    -0.25
    วà¸Ķ
    -0.23
    鼶
    -0.23
    åı¶
    -0.23
     Instant
    -0.23
    éĹ´è·Ŀ
    -0.23
    à¹Ģหล
    -0.23
    infeld
    -0.22
    POSITIVE LOGITS
     parade
    0.28
    ç´¯äºĨ
    0.26
     haus
    0.25
    laps
    0.25
    vere
    0.25
    å°±æĺ¯ä¸Ģ个
    0.24
     Starr
    0.24
    æĥ³èµ·æĿ¥
    0.23
    çī¢è®°
    0.23
    ral
    0.23
    Activations Density 1.476%

    No Known Activations