© 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. 49521
    Prev
    Next
    INDEX
    Explanations

    granite and quartz

    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
    ened
    -0.11
    åıijå±ķ壮大
    -0.10
    éºĩ
    -0.10
    ç¼±
    -0.09
    éĻIJæľŁ
    -0.09
    æĢ§åij½
    -0.09
    ç¿©
    -0.09
    ings
    -0.09
    itative
    -0.09
    raries
    -0.09
    POSITIVE LOGITS
    обÑĢ
    0.09
    forth
    0.08
    earch
    0.08
    etsk
    0.08
    Ľå»º
    0.08
    æīĭ
    0.08
    dish
    0.08
    коÑģ
    0.08
    leigh
    0.08
    IME
    0.08
    Activations Density 0.003%

    No Known Activations