© 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. 56134
    Prev
    Next
    INDEX
    Explanations

    alt, altitude, alt-right, altrows

    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
    naire
    -0.12
    ãģıãĤĭ
    -0.10
    rade
    -0.09
    ngo
    -0.09
    byn
    -0.09
    kle
    -0.09
    stag
    -0.09
     Ips
    -0.09
    ildo
    -0.08
    das
    -0.08
    POSITIVE LOGITS
    itude
    0.13
    itudes
    0.12
    ë¡Ŀ
    0.11
    ITUDE
    0.10
    vely
    0.10
    ansas
    0.09
    geme
    0.09
    itud
    0.09
    WAYS
    0.09
    coins
    0.09
    Activations Density 0.023%

    No Known Activations