© 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. 38916
    Prev
    Next
    INDEX
    Explanations

    man, manhattan, manually, management, manias

    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
    andre
    -0.10
     niekt
    -0.10
    _locals
    -0.10
    _lineno
    -0.10
    issen
    -0.09
    ë¹Ļ
    -0.09
    ten
    -0.09
    elsey
    -0.09
    ted
    -0.09
    /from
    -0.09
    POSITIVE LOGITS
    hattan
    0.12
    made
    0.12
    agment
    0.11
    ifold
    0.11
    pages
    0.10
    /man
    0.10
    fred
    0.09
    (man
    0.09
    lit
    0.09
    -made
    0.09
    Activations Density 0.045%

    No Known Activations