© 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. 87358
    Prev
    Next
    INDEX
    Explanations

    that

    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
    çĤİ
    -0.31
    trait
    -0.27
    én
    -0.27
    [href
    -0.26
    ä¹¾åĿ¤
    -0.26
     types
    -0.26
    ymes
    -0.26
    ant
    -0.26
    iter
    -0.25
    ries
    -0.25
    POSITIVE LOGITS
    Century
    0.26
    ERA
    0.26
    *out
    0.25
    毫æĹłçĸij
    0.24
    omnia
    0.24
    éĹ»åIJį
    0.24
    å¾Īå¤ļ
    0.23
     Rel
    0.23
    åIJĥè¿ĩ
    0.23
    boro
    0.23
    Activations Density 0.004%

    No Known Activations