© 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. 23170
    Prev
    Next
    INDEX
    Explanations

    serious or mad intensifier

    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
    åĬ±
    -0.10
    æħ·
    -0.10
    é¬ĺ
    -0.09
    彩èī²
    -0.09
    踮
    -0.09
    asd
    -0.09
    彩
    -0.08
    沧
    -0.08
    agas
    -0.08
    çł´äº§
    -0.08
    POSITIVE LOGITS
    çĽ¸äº²
    0.09
    带åĽŀ
    0.09
    çĪ¸
    0.09
    æĶ¶åıĸ
    0.08
     Nes
    0.08
    jee
    0.08
    æĸ¯å¡Ķ
    0.08
    亲
    0.08
    DEF
    0.08
     salute
    0.08
    Activations Density 0.085%

    No Known Activations