© 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. 129568
    Prev
    Next
    INDEX
    Explanations

    Text fragments

    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
    ä¸Ģç»ı
    -0.26
    unday
    -0.24
     happening
    -0.24
    (integer
    -0.24
    ãģķãģĦ
    -0.24
    .openapi
    -0.24
     shifts
    -0.24
     Happ
    -0.23
     HAPP
    -0.23
    åѦ
    -0.23
    POSITIVE LOGITS
    ocked
    0.33
    bound
    0.28
     amplify
    0.26
     déco
    0.25
    çĥ½
    0.25
    ativ
    0.25
    积累
    0.25
    éı¡
    0.25
    oods
    0.24
    лÑİд
    0.24
    Activations Density 0.009%

    No Known Activations