© 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. 31309
    Prev
    Next
    INDEX
    Explanations

    opening followed by event/part nouns

    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
    çĦ¶æĺ¯
    -0.12
    ominated
    -0.11
    hud
    -0.09
    åĺ´éĩĮ
    -0.09
    aceous
    -0.09
    -0.09
    èĤļ
    -0.09
    ëį°
    -0.09
    SYS
    -0.08
    heid
    -0.08
    POSITIVE LOGITS
    èŤ
    0.09
    /or
    0.09
    -opening
    0.08
    pects
    0.08
    dorf
    0.08
    ts
    0.08
     Julien
    0.08
    æ»ĭ
    0.08
    çĿ«
    0.08
    nit
    0.08
    Activations Density 0.024%

    No Known Activations