© 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. 98030
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    æµ·æ¹¾
    -0.27
    ough
    -0.25
    -instance
    -0.25
    _SI
    -0.24
    utes
    -0.23
    -trained
    -0.22
    çĵ¢
    -0.22
    æĺµ
    -0.22
    eland
    -0.22
    deliver
    -0.22
    POSITIVE LOGITS
     col
    0.27
    igate
    0.25
    kees
    0.24
    :maj
    0.24
    (col
    0.23
     deutschland
    0.23
    :right
    0.23
    .updateDynamic
    0.23
    ichern
    0.23
    å¦Ĥä½ķ
    0.22
    Activations Density 0.011%

    No Known Activations