© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    never followed by a verb

    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
    sWith
    -0.09
    çݯåį«
    -0.09
    scar
    -0.09
    бег
    -0.08
    æ³¢
    -0.08
    åŃIJåŃĻ
    -0.08
    ãģ¾ãģĹãģ¦
    -0.08
    æĺ¥é£İ
    -0.08
    ä¸ĩæĪ·
    -0.08
     Scre
    -0.08
    POSITIVE LOGITS
    theless
    0.18
    -ending
    0.11
    ationToken
    0.10
    heel
    0.10
    dera
    0.09
    á»įng
    0.09
    è¿ĩé«ĺ
    0.09
    Ä°M
    0.09
    ataire
    0.09
    chia
    0.09
    Activations Density 0.023%

    No Known Activations