© 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. 112175
    Prev
    Next
    INDEX
    Explanations

    blindness

    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
    zy
    -0.26
    ä¾ĭå¤ĸ
    -0.24
    verage
    -0.24
    èĢĥè¯ģ
    -0.24
     logic
    -0.24
    еÑĢÑĮ
    -0.24
    Emb
    -0.23
     Logic
    -0.23
     getCode
    -0.23
    御
    -0.23
    POSITIVE LOGITS
    çĽ²
    0.28
    çªģå¦Ĥ
    0.26
    çľĭä¸įè§ģ
    0.25
    [vi
    0.25
    WARDED
    0.25
    __["
    0.24
    累累
    0.24
     mù
    0.23
    éĩįä¸Ńä¹ĭéĩį
    0.23
    æij¸ç´¢
    0.23
    Activations Density 0.002%

    No Known Activations