© 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. 5730
    Prev
    Next
    INDEX
    Explanations

    open source project

    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
    oret
    -0.11
    olly
    -0.10
    oral
    -0.09
    .prevent
    -0.09
    çĽĪ
    -0.09
    æĭ±
    -0.09
    osoph
    -0.09
    å¦Ĥæŀľè¯´
    -0.09
    requ
    -0.08
    oria
    -0.08
    POSITIVE LOGITS
    -minded
    0.10
    nings
    0.10
    ä½Ĩæĺ¯åľ¨
    0.10
    gang
    0.09
    åIJĮæĹ¶ä¹Ł
    0.09
    visor
    0.09
    ward
    0.09
    eft
    0.09
    NING
    0.09
    ifting
    0.09
    Activations Density 0.021%

    No Known Activations