© 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. 27048
    Prev
    Next
    INDEX
    Explanations

    age

    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
    ê»ĺ
    -0.12
    zos
    -0.10
    à¹Į
    -0.10
    ry
    -0.10
    ness
    -0.09
    erer
    -0.09
    chet
    -0.09
    AsyncResult
    -0.09
    mute
    -0.09
    oman
    -0.08
    POSITIVE LOGITS
    0.14
    ged
    0.10
    letic
    0.10
    brush
    0.10
    ood
    0.10
    -old
    0.10
    overnment
    0.09
    ording
    0.09
    keeping
    0.09
    леÑĢ
    0.09
    Activations Density 0.052%

    No Known Activations