© 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. 22-TRANSCODER-HP
    7. 87874
    Prev
    Next
    INDEX
    Explanations

    Mentions years/dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictionary
    -0.24
     fins
    -0.24
    åĨĢ
    -0.24
    ENTS
    -0.24
    rts
    -0.23
    ä¸įçŁ¥
    -0.23
     gul
    -0.23
    请çĤ¹åĩ»
    -0.23
     Pods
    -0.23
     agreements
    -0.23
    POSITIVE LOGITS
    æ¯ıåij¨
    0.26
    éĽªèĬ±
    0.25
    [âĢ¦
    0.25
    au
    0.24
    .stat
    0.24
    åij¨å²ģ
    0.24
     Sharp
    0.24
    ä¸İæŶ
    0.24
    éĴĿ
    0.23
    缸åıį
    0.23
    Activations Density 0.006%

    No Known Activations