© 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. 98490
    Prev
    Next
    INDEX
    Explanations

    Verbs

    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
    以åıĬ
    -0.27
    iens
    -0.25
     serialVersionUID
    -0.24
    gün
    -0.24
    hardware
    -0.24
     oltre
    -0.24
    é¹ľ
    -0.24
    exists
    -0.24
    çłĶ究ä¸Ńå¿ĥ
    -0.23
     cot
    -0.23
    POSITIVE LOGITS
    ing
    0.51
    ifying
    0.33
    ING
    0.32
    eting
    0.31
    è²Į
    0.31
    oting
    0.31
    ities
    0.30
    ning
    0.30
    owing
    0.30
    ising
    0.29
    Activations Density 0.011%

    No Known Activations