© 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. 49614
    Prev
    Next
    INDEX
    Explanations

    aquarium, sesame, targeting

    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
    ings
    -0.11
    adic
    -0.10
    dre
    -0.09
    ìĭ¶
    -0.09
    /or
    -0.09
    rix
    -0.09
    ×ķת
    -0.09
    itude
    -0.08
    pai
    -0.08
    mor
    -0.08
    POSITIVE LOGITS
    keit
    0.12
    è§ĴèIJ½
    0.11
    WSC
    0.10
    erate
    0.10
    eer
    0.09
    ousel
    0.09
    ç¤ģ
    0.09
    ellaneous
    0.09
    åģ»
    0.09
    åľ°å¸¦
    0.09
    Activations Density 0.003%

    No Known Activations