© 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. 30039
    Prev
    Next
    INDEX
    Explanations

    concentration

    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
    illard
    -0.28
     fı
    -0.26
    ä»Ĭ天æĪij们
    -0.26
     enjo
    -0.26
     ”↵↵
    -0.25
     mojo
    -0.25
    åĨ¬
    -0.24
    åİĦ
    -0.24
    åħħæ²Ľ
    -0.24
    imately
    -0.24
    POSITIVE LOGITS
    obil
    0.33
    åĬĿ
    0.26
    å¢Ļ
    0.26
    åıijçİ°èĩªå·±
    0.26
    sein
    0.26
    éĶ®çĽĺ
    0.24
    ç¬Ķ
    0.24
    纺
    0.24
    èľ¡
    0.24
     diver
    0.24
    Activations Density 0.515%

    No Known Activations