© 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. 129555
    Prev
    Next
    INDEX
    Explanations

    scientific problems

    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
     motivated
    -0.32
     reason
    -0.28
    çļĦåİŁåĽł
    -0.27
    Toolkit
    -0.27
    级
    -0.26
    åĬ¨æijĩ
    -0.26
    ä¹ĭæīĢ以
    -0.26
    _REASON
    -0.25
     motivations
    -0.25
     formed
    -0.25
    POSITIVE LOGITS
    urrenc
    0.28
     Affero
    0.27
    åģ¿
    0.26
    roe
    0.26
    ä¸İåIJ¦
    0.26
    grave
    0.25
     Lad
    0.24
    å¥
    0.24
     Affordable
    0.24
    adelphia
    0.23
    Activations Density 0.016%

    No Known Activations