© 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. 63316
    Prev
    Next
    INDEX
    Explanations

    ruth lessly, -fulness, -istic

    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
    issor
    -0.10
    -minded
    -0.09
    .utf
    -0.09
    没æĶ¶
    -0.09
    ../../../
    -0.09
     Infect
    -0.09
    ULAR
    -0.09
    ERO
    -0.09
    åĪ©å¥½
    -0.09
    åIJįè¯į
    -0.09
    POSITIVE LOGITS
    lessly
    0.15
    fully
    0.12
    ably
    0.11
    fulness
    0.10
    istic
    0.10
    ioni
    0.09
    ingly
    0.09
    listed
    0.09
    lessness
    0.09
    Ñĥв
    0.09
    Activations Density 0.013%

    No Known Activations