© 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. 97540
    Prev
    Next
    INDEX
    Explanations

    Code, email, legal documents

    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
    serter
    -0.23
    dÃŃ
    -0.23
    å½ĵä¹ĭ
    -0.23
    åĨħå¤ĸ
    -0.23
    ually
    -0.23
     kittens
    -0.22
    -kit
    -0.22
    DAQ
    -0.22
     spe
    -0.21
    tone
    -0.21
    POSITIVE LOGITS
    å¾®åķĨ
    0.23
    putc
    0.22
    lich
    0.22
    айÑĤе
    0.21
    choose
    0.21
    (Thread
    0.21
    (Screen
    0.20
    ãģ¾ãģĹãģ¦
    0.20
    åı¦ä¸ĢåįĬ
    0.20
    çĿĢçľ¼
    0.20
    Activations Density 0.009%

    No Known Activations