© 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. 50199
    Prev
    Next
    INDEX
    Explanations

    cortical

    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
    ëģĶ
    -0.13
    ÑģÑı
    -0.09
    дÑĢ
    -0.09
    ãģĻãģ§ãģ«
    -0.09
    rik
    -0.09
    ked
    -0.08
    ãģįãģ£ãģ¨
    -0.08
    åľª
    -0.08
    iti
    -0.08
    abo
    -0.08
    POSITIVE LOGITS
    ez
    0.11
    ium
    0.09
    igon
    0.09
    ormap
    0.09
    åĵĩ
    0.09
    alte
    0.09
    åĬĽéĩı
    0.09
    entions
    0.09
    inator
    0.08
    _Action
    0.08
    Activations Density 0.043%

    No Known Activations