© 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. 56508
    Prev
    Next
    INDEX
    Explanations

    or introducing alternatives

    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
    edic
    -0.10
     вÑģÑı
    -0.10
    Unmarshaller
    -0.10
    äºĽè®¸
    -0.10
    äºĨäºĽ
    -0.10
    .defaultValue
    -0.09
    è§ħ
    -0.09
    acho
    -0.09
    ç²²
    -0.09
    ows
    -0.09
    POSITIVE LOGITS
    å·
    0.10
    sha
    0.08
    igin
    0.07
    -most
    0.07
    “
    0.07
     hasattr
    0.07
    pel
    0.07
    -
    0.07
     fran
    0.07
     hands
    0.07
    Activations Density 0.026%

    No Known Activations