© 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. 33757
    Prev
    Next
    INDEX
    Explanations

    names of people and places like Howell, Davenport, Caswell, McDowell

    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
    alysis
    -0.12
    osphere
    -0.10
    ificant
    -0.09
    eness
    -0.09
    -0.09
    nection
    -0.09
    俸
    -0.09
    æŀ°
    -0.08
    enes
    -0.08
    ëł¹
    -0.08
    POSITIVE LOGITS
    ìĸ¸
    0.09
    年代
    0.09
    nan
    0.08
    ren
    0.08
    ately
    0.08
    ä»ĭç»įä¸Ģä¸ĭ
    0.08
    ä½ıåĿĢ
    0.08
    reno
    0.08
    ECH
    0.08
    æĢ»çIJĨ
    0.08
    Activations Density 0.003%

    No Known Activations