© 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. 33711
    Prev
    Next
    INDEX
    Explanations

    noscript / no further / no longer

    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
    à¹Į
    -0.11
    ä¸įéĶĻçļĦ
    -0.09
    -tooltip
    -0.09
    éĺĶ
    -0.09
    wise
    -0.09
    åIJĦèĩªçļĦ
    -0.09
    like
    -0.09
    unde
    -0.08
    .Marshal
    -0.08
    forth
    -0.08
    POSITIVE LOGITS
    zzle
    0.13
    xious
    0.12
    ël
    0.11
    thern
    0.11
    /no
    0.11
    ether
    0.11
    veau
    0.11
    theast
    0.11
     اÙĦشرÙĬÙģ
    0.10
     Desmond
    0.10
    Activations Density 0.113%

    No Known Activations