© 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. 57932
    Prev
    Next
    INDEX
    Explanations

    Lucas

    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
    ening
    -0.14
    ened
    -0.10
    oral
    -0.10
    zza
    -0.09
    orary
    -0.09
    jud
    -0.09
    icy
    -0.09
    eenth
    -0.09
    beat
    -0.08
    ÑĩÑĮ
    -0.08
    POSITIVE LOGITS
    teenth
    0.10
    åįĩéĻį
    0.09
    ry
    0.09
    azzi
    0.09
    åŃĶ
    0.09
    adia
    0.09
    илÑģÑı
    0.09
    ãģĤãĤĭç¨ĭ度
    0.09
    ics
    0.09
    ÑĤив
    0.09
    Activations Density 0.007%

    No Known Activations