© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    place of

    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
    ship
    -0.12
    ists
    -0.11
    à¹Į
    -0.11
    emia
    -0.10
    adal
    -0.10
    moz
    -0.10
    -sided
    -0.09
    rog
    -0.09
    ships
    -0.09
    aph
    -0.09
    POSITIVE LOGITS
    bos
    0.13
    HOLDER
    0.12
    holders
    0.12
    ëģĶ
    0.12
    enta
    0.12
     Ñģобой
    0.11
    arity
    0.11
    iful
    0.10
    OfBirth
    0.10
    finder
    0.10
    Activations Density 0.070%

    No Known Activations