© 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. 29795
    Prev
    Next
    INDEX
    Explanations

    Actions/Experiences

    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
    å¾ĹçĽĬ
    -0.29
     delights
    -0.25
     callBack
    -0.25
    ãģĦãģ¾
    -0.24
    强æľīåĬĽ
    -0.24
     Demp
    -0.24
     charcoal
    -0.23
    è·³
    -0.23
    iÄħ
    -0.23
     Greenwood
    -0.23
    POSITIVE LOGITS
    кÑĥп
    0.28
    æĦŁ
    0.26
    çĸ¤
    0.25
    á»·
    0.25
     pea
    0.25
    лив
    0.24
    箪
    0.24
    常è§ģçļĦ
    0.24
     clearTimeout
    0.24
    .edu
    0.24
    Activations Density 1.688%

    No Known Activations