© 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. 57614
    Prev
    Next
    INDEX
    Explanations

    extraordinary followed by adjectives

    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
    ature
    -0.09
    ëĭ¤ê°Ģ
    -0.09
    wise
    -0.09
    Ñĩив
    -0.08
     Äijỡ
    -0.08
    ena
    -0.08
    ver
    -0.08
    éĺ¶æ¢¯
    -0.08
    inding
    -0.08
    ак
    -0.08
    POSITIVE LOGITS
    éĿŀåĩ¡
    0.11
    lös
    0.10
    è¡ħ
    0.09
    arov
    0.09
    åĻĺ
    0.09
    DataExchange
    0.09
    alon
    0.09
    ÙĬÙĬÙĨ
    0.09
    éªħ
    0.09
    lander
    0.09
    Activations Density 0.006%

    No Known Activations