© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52420
    Prev
    Next
    INDEX
    Explanations

    are/were going

    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
    ãģĹãģ¾ãģĨ
    -0.12
    di
    -0.10
    éŃĦ
    -0.09
    ile
    -0.09
    dos
    -0.09
    dz
    -0.08
    dom
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    dc
    -0.08
    Ķ
    -0.08
    POSITIVE LOGITS
     gonna
    0.11
    ighth
    0.09
    å§ĭ
    0.09
    bia
    0.09
    geois
    0.09
    ngine
    0.09
    hof
    0.09
    媳
    0.09
    vell
    0.09
    ibold
    0.09
    Activations Density 0.021%

    No Known Activations