© 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. 88366
    Prev
    Next
    INDEX
    Explanations

    similar

    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
    sudo
    -0.26
    ymous
    -0.23
    eph
    -0.23
    ellant
    -0.23
    sec
    -0.23
    sched
    -0.23
    ensible
    -0.23
    illon
    -0.22
    sites
    -0.22
    mere
    -0.22
    POSITIVE LOGITS
    kest
    0.25
    åIJĮçŃī
    0.24
     cascade
    0.24
    çĶ¨å·¥
    0.24
     heat
    0.23
    ARA
    0.23
    hood
    0.23
    arity
    0.23
    ateral
    0.23
    encing
    0.23
    Activations Density 0.244%

    No Known Activations