© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    record deal, label, store, companies, producer

    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
    ary
    -0.09
    -rated
    -0.09
    endid
    -0.09
    ijkl
    -0.09
    POSIT
    -0.09
    agma
    -0.08
    _RESOLUTION
    -0.08
    ith
    -0.08
    illi
    -0.08
    chy
    -0.08
    POSITIVE LOGITS
    -breaking
    0.11
    ings
    0.11
    keeping
    0.10
    äºĭåĦ¿
    0.10
    lc
    0.09
    çķĮçļĦ
    0.09
    SSION
    0.09
    stime
    0.09
    Face
    0.09
    tro
    0.08
    Activations Density 0.024%

    No Known Activations