© 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. 54237
    Prev
    Next
    INDEX
    Explanations

    hair styling and treatments

    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
    ively
    -0.11
    èĩªæľī
    -0.09
    bih
    -0.09
    amina
    -0.08
     Eig
    -0.08
    åĨħåľ°
    -0.08
    çĩĥæ²¹
    -0.08
    æ´¹
    -0.08
    æ¯Ķäºļ
    -0.08
    -style
    -0.08
    POSITIVE LOGITS
    cuts
    0.11
    绪
    0.10
    drop
    0.09
    shake
    0.09
    ÑĢоÑģÑĤ
    0.09
    deen
    0.09
    ousse
    0.09
    åĪ¶åĵģ
    0.09
    agan
    0.08
    çĬ¶åĨµ
    0.08
    Activations Density 0.014%

    No Known Activations