© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    actual followed by a noun

    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
    é«ĺçļĦ
    -0.09
     ÑģобÑģÑĤвенно
    -0.09
    Å¡t
    -0.09
    _mux
    -0.08
    éĶĨ
    -0.08
    广çĶµ
    -0.08
    emand
    -0.08
    ormal
    -0.08
    å·¥ä½ľç«Ļ
    -0.08
    oom
    -0.08
    POSITIVE LOGITS
    ity
    0.15
    mente
    0.13
    ities
    0.13
    ités
    0.13
    ité
    0.09
    istically
    0.09
    ä¸įæĩĪ
    0.09
    ationship
    0.09
    itives
    0.09
    istic
    0.09
    Activations Density 0.017%

    No Known Activations