© 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. 22946
    Prev
    Next
    INDEX
    Explanations

    difficulty or ease

    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
     raw
    -0.09
    ogle
    -0.09
    èĥĥåı£
    -0.09
    é²ĩ
    -0.08
    袱
    -0.08
     equ
    -0.08
    ows
    -0.08
    åĩ½
    -0.08
    INGTON
    -0.08
    ableObject
    -0.08
    POSITIVE LOGITS
    CHA
    0.10
    æ®Ĩ
    0.09
    _spell
    0.09
    ;display
    0.09
    getDisplay
    0.09
    é«ĺè´µ
    0.09
    endo
    0.08
    acker
    0.08
    .easy
    0.08
    оÑģÑĮ
    0.08
    Activations Density 0.033%

    No Known Activations