© 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. 9-TRANSCODER-HP
    7. 29649
    Prev
    Next
    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offs
    -0.27
    tlement
    -0.25
    é¾Ī
    -0.25
    .terminate
    -0.24
     ab
    -0.24
    apixel
    -0.23
    leader
    -0.23
     approaching
    -0.23
    éĵ
    -0.23
    åŃ¦æľŁ
    -0.23
    POSITIVE LOGITS
    çŃ·åŃIJ
    0.29
    collision
    0.24
     collision
    0.24
     Priority
    0.24
    atsu
    0.24
     priority
    0.24
     Lynch
    0.23
     kir
    0.23
    untu
    0.23
    å¥ĩå¼Ĥ
    0.23
    Activations Density 3.505%

    No Known Activations