© 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. 54150
    Prev
    Next
    INDEX
    Explanations

    clean energy and fuels

    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
    奢ä¾Ī
    -0.10
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    lke
    -0.09
    楸
    -0.09
    ETO
    -0.09
    ä¾Ŀæ³ķ追究
    -0.09
    ä¿ħ
    -0.09
    åĬŁå¤«
    -0.08
    佩æľį
    -0.08
    èĩªç§°
    -0.08
    POSITIVE LOGITS
    æĽ¿ä»£
    0.10
    æĽ¿æį¢
    0.09
     substitution
    0.09
    åѤ
    0.09
    Penn
    0.09
    åįłæ¯Ķ
    0.09
     penn
    0.09
    .createFrom
    0.09
     DeV
    0.09
     substitutions
    0.09
    Activations Density 0.046%

    No Known Activations