© 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. 29780
    Prev
    Next
    INDEX
    Explanations

    exceptions and errors

    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
     Wolff
    -0.30
    arez
    -0.25
     Lange
    -0.25
    speed
    -0.24
    axy
    -0.24
    裳
    -0.24
    -rest
    -0.24
     Weiss
    -0.24
     Isle
    -0.23
    Hold
    -0.23
    POSITIVE LOGITS
    ä¸įçĶ±
    0.28
    åĮħåĮħ
    0.28
    ITCH
    0.28
     fairy
    0.25
     favourite
    0.25
    å±ŀäºİèĩªå·±
    0.25
    æĬĵ好
    0.25
    venues
    0.24
     Canberra
    0.24
    gradable
    0.24
    Activations Density 2.483%

    No Known Activations