© 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. 34466
    Prev
    Next
    INDEX
    Explanations

    squ

    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
    ãĥ£
    -0.09
    ents
    -0.08
    غا
    -0.08
    aven
    -0.08
    yms
    -0.08
    /alert
    -0.08
    agan
    -0.08
    olis
    -0.08
    ponse
    -0.08
    çĤ·
    -0.08
    POSITIVE LOGITS
    好åĩłä¸ª
    0.10
    说çĿĢ
    0.09
    äºĨä¸įå°ij
    0.09
    è§ģæķĪ
    0.09
    weg
    0.09
    amate
    0.09
    iest
    0.09
    _bulk
    0.09
    elite
    0.09
    dio
    0.09
    Activations Density 0.021%

    No Known Activations