© 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. 33264
    Prev
    Next
    INDEX
    Explanations

    Waldorf, Walden, Wealden

    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
    ality
    -0.13
    TING
    -0.10
    ä¹ĭå¤Ħ
    -0.10
    nels
    -0.09
    apore
    -0.09
    NEL
    -0.09
    åĽ¢éķ¿
    -0.09
    ãģ¡ãģ¯
    -0.09
    cake
    -0.09
    ctor
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.10
    -fashioned
    0.10
    osterone
    0.09
    spar
    0.09
    ä¸įç»ı
    0.08
    ian
    0.08
    frei
    0.08
    ays
    0.08
    usz
    0.08
    ä¾¿å®ľ
    0.08
    Activations Density 0.005%

    No Known Activations