© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50632
    Prev
    Next
    INDEX
    Explanations

    mult

    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
    zelf
    -0.11
    umpt
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ving
    -0.09
    çIJ¢
    -0.09
    ../
    -0.09
    auty
    -0.09
    aten
    -0.09
    inite
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
    IPLE
    0.13
    verständlich
    0.11
    ilater
    0.11
    -purpose
    0.10
    ivariate
    0.10
    ändig
    0.10
    çĹĩ
    0.10
    tle
    0.10
    pliers
    0.09
    èĨĽ
    0.09
    Activations Density 0.042%

    No Known Activations