© 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. 20-TRANSCODER-HP
    7. 141892
    Prev
    Next
    INDEX
    Explanations

    possibility/conditionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comb
    -0.27
    Jack
    -0.25
    ä¸ĭ乡
    -0.25
    /std
    -0.25
     Bought
    -0.24
    æį¡
    -0.24
    çĨ¬å¤ľ
    -0.24
    @email
    -0.24
     Cron
    -0.24
    umat
    -0.23
    POSITIVE LOGITS
    vasive
    0.27
    иж
    0.25
     improv
    0.24
    éĩİçĶŁ
    0.24
     kingdoms
    0.24
    tweets
    0.24
    [S
    0.23
    FUL
    0.23
    "</
    0.23
    bin
    0.23
    Activations Density 25.086%

    No Known Activations