© 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. 35083
    Prev
    Next
    INDEX
    Explanations

    cs degree or job

    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
    身å¿ĥ
    -0.10
    edList
    -0.10
    edImage
    -0.09
    ãģ¶ãĤĬ
    -0.09
    海峡
    -0.09
    .kotlin
    -0.09
    æ»ĭ
    -0.08
    typings
    -0.08
    aldo
    -0.08
    OCI
    -0.08
    POSITIVE LOGITS
    _SHA
    0.09
    缩水
    0.09
    tracts
    0.09
    ÄŃ
    0.09
    0.08
    -shadow
    0.08
    cial
    0.08
     bald
    0.08
    	TokenName
    0.08
    dl
    0.08
    Activations Density 0.034%

    No Known Activations