© 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. 98791
    Prev
    Next
    INDEX
    Explanations

    Textual data

    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
    ights
    -0.32
    Servers
    -0.28
     esl
    -0.27
     Servers
    -0.25
    .combine
    -0.25
    ä¸ĢéĿ¢
    -0.24
    ivery
    -0.24
    orget
    -0.24
     Sofa
    -0.24
    ThanOrEqualTo
    -0.24
    POSITIVE LOGITS
    ent
    0.27
    ensible
    0.27
     ent
    0.27
     Ent
    0.27
     ENT
    0.26
    äºļ
    0.26
    Ent
    0.26
    ätz
    0.25
    ulk
    0.25
    tered
    0.25
    Activations Density 0.001%

    No Known Activations