© 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. 3214
    Prev
    Next
    INDEX
    Explanations

    quantities and counts

    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
    æ»ĭåij³
    -0.10
    closure
    -0.10
    apel
    -0.10
    istrate
    -0.09
    emean
    -0.09
    zeich
    -0.09
    URE
    -0.09
    деÑĤ
    -0.09
    URES
    -0.09
    åĪ»
    -0.09
    POSITIVE LOGITS
     amount
    0.09
    è¶Ĭæĺ¯
    0.08
    ertext
    0.08
    年产åĢ¼
    0.08
    çłĶåıijæĬķåħ¥
    0.08
    ãģ«ãģ¨ãģ£ãģ¦
    0.08
    NIL
    0.08
    OrNull
    0.08
     rate
    0.08
    ä½Ī
    0.07
    Activations Density 0.596%

    No Known Activations