© 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. 23067
    Prev
    Next
    INDEX
    Explanations

    See the, All rights

    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
    ackbar
    -0.09
    ductive
    -0.09
    rastructure
    -0.09
    opup
    -0.08
    以åıĬåħ¶ä»ĸ
    -0.08
    adays
    -0.08
    etc
    -0.08
    uded
    -0.08
    [@
    -0.08
    acons
    -0.08
    POSITIVE LOGITS
    orem
    0.21
    ä¹ŁåĽłæѤ
    0.14
    oret
    0.14
    ories
    0.14
     ведÑĮ
    0.13
    ÑīиÑĤ
    0.12
    oretical
    0.12
    erdings
    0.11
    iming
    0.11
    pire
    0.11
    Activations Density 2.101%

    No Known Activations