© 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. 61289
    Prev
    Next
    INDEX
    Explanations

    spaghetti dinner or haricot verts

    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
    sey
    -0.09
    iant
    -0.08
    ä»¥äººä¸ºæľ¬
    -0.08
    epad
    -0.08
    esium
    -0.08
    Regression
    -0.08
    edList
    -0.08
     Regression
    -0.08
    _regression
    -0.08
    ally
    -0.08
    POSITIVE LOGITS
    ties
    0.09
    åıįæŃ£
    0.09
    çĤĶ
    0.09
    orno
    0.09
    æİĤ
    0.09
    BILL
    0.09
    èĭĹ
    0.09
    MAP
    0.09
    åľ°ä¸Ńæµ·
    0.08
    weed
    0.08
    Activations Density 0.001%

    No Known Activations