© 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. 50093
    Prev
    Next
    INDEX
    Explanations

    hobby and related activities

    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
    絡
    -0.10
    urator
    -0.10
    -cut
    -0.09
    quer
    -0.08
    -reaching
    -0.08
    soever
    -0.08
    ains
    -0.08
    íĶ½
    -0.08
    -Origin
    -0.08
    NCY
    -0.08
    POSITIVE LOGITS
    ellaneous
    0.11
    è¨ĢãģĪãģ°
    0.11
    æĢı
    0.11
    åĭĥåĭĥ
    0.10
    akk
    0.09
    çĸĻ
    0.09
    dale
    0.09
    çĪ±å¥½
    0.09
    dle
    0.09
    æģĻ
    0.09
    Activations Density 0.003%

    No Known Activations