© 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. 57850
    Prev
    Next
    INDEX
    Explanations

    coming or bringing

    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
    ç£Ķ
    -0.09
    forming
    -0.08
    sheets
    -0.08
    éĢģ
    -0.08
    å¸ĥ
    -0.08
    rat
    -0.08
     Specs
    -0.08
    AMS
    -0.08
     HY
    -0.07
    uli
    -0.07
    POSITIVE LOGITS
    è´©
    0.10
    å¨Ħ
    0.10
    éļIJéļIJ
    0.10
    apel
    0.10
    棱
    0.10
    è·³åĩº
    0.10
    æĨ¬
    0.09
    è¿Ļ家ä¼Ļ
    0.09
    åįļçī©é¦Ĩ
    0.09
    ousel
    0.09
    Activations Density 0.030%

    No Known Activations