© 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. 55966
    Prev
    Next
    INDEX
    Explanations

    adaptation/adapting books/films

    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
    æŬ
    -0.10
     Kramer
    -0.09
    åijĺ
    -0.08
    ANGLE
    -0.08
    enc
    -0.08
    ç¾İè²Į
    -0.08
    mek
    -0.08
    ocha
    -0.08
    valid
    -0.08
     published
    -0.08
    POSITIVE LOGITS
    çļĦåľ°åĽ¾
    0.10
    èĺħ
    0.10
    çļĦä¸ĸçķĮ
    0.09
    æµģ泪
    0.09
    urre
    0.09
    зоÑĢ
    0.08
    ç§ķ
    0.08
    åŃĹåı·
    0.08
    éļıå¤Ħ
    0.08
    allas
    0.08
    Activations Density 0.033%

    No Known Activations