© 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. 87699
    Prev
    Next
    INDEX
    Explanations

    Code/not well-formed English

    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
    èĤ¢
    -0.33
    åı¯è§ģ
    -0.29
    _DEN
    -0.25
    веÑģ
    -0.24
    éŀħ
    -0.24
     consequ
    -0.24
    âİ¥
    -0.23
    èĦĤèĤª
    -0.23
    åĪ¶èį¯
    -0.23
     Close
    -0.23
    POSITIVE LOGITS
    åħ¨åľº
    0.32
    éĻĦåĬł
    0.31
     overall
    0.30
     general
    0.29
     Mixed
    0.29
    misc
    0.28
    overall
    0.28
    PickerController
    0.28
    -summary
    0.27
    combined
    0.27
    Activations Density 0.006%

    No Known Activations