© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1330
    Prev
    Next
    INDEX
    Explanations

    injured or wounded extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¦Ľ
    -0.10
    æļĿ
    -0.09
    çªĿ
    -0.09
    èŀŁ
    -0.09
    xor
    -0.09
    ä»ĸå¦Ī
    -0.09
    åħľ
    -0.09
    åĽŀäºĭ
    -0.09
    hardt
    -0.09
    åĬŁ
    -0.09
    POSITIVE LOGITS
    缪
    0.10
    lut
    0.10
    çĶļèĩ³
    0.09
    ç¬ĥ
    0.08
    iles
    0.08
    çĻ¾ç§ij
    0.08
    oley
    0.08
    Occurred
    0.08
    æµģåħ¥
    0.08
    GES
    0.08
    Activations Density 0.010%

    No Known Activations