© 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. 130841
    Prev
    Next
    INDEX
    Explanations

    Code, technical writing

    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
    Central
    -0.24
     ÑĢоман
    -0.23
    emente
    -0.23
    å®ł
    -0.23
     Central
    -0.22
    çļĦéĥ¨åĪĨ
    -0.22
    æ´Ĺ
    -0.22
    ↵     ↵
    -0.22
    ,obj
    -0.22
    -piece
    -0.22
    POSITIVE LOGITS
    aising
    0.26
    lod
    0.25
    åŁºéĩij管çIJĨ
    0.24
    èĪī
    0.24
    è§Ģ
    0.24
    crest
    0.24
    rikes
    0.24
     bed
    0.23
    .ga
    0.23
    js
    0.23
    Activations Density 0.004%

    No Known Activations