© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8235
    Prev
    Next
    INDEX
    Explanations

    SIG followed by special terms

    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
    ï¸
    -0.09
    åħļå§Ķ
    -0.09
    管å±Ģ
    -0.08
    èĢģçϾå§ĵ
    -0.08
    媳
    -0.08
    near
    -0.08
    ç¬Ļ
    -0.08
    èħĪ
    -0.08
    å±ĢéĿ¢
    -0.08
    oken
    -0.08
    POSITIVE LOGITS
    urd
    0.13
    ORN
    0.09
    riger
    0.09
    .fre
    0.09
    lient
    0.09
    даÑİÑĤ
    0.09
    ENCES
    0.09
    enced
    0.09
    ences
    0.09
    ÓĢ
    0.09
    Activations Density 0.023%

    No Known Activations