© 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. 30499
    Prev
    Next
    INDEX
    Explanations

    wet, slippery surfaces

    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
    人å±ħ
    -0.10
    é¼ł
    -0.09
    çĨĬ
    -0.09
    èļģ
    -0.09
    çŁ¥
    -0.09
    enting
    -0.08
    estruct
    -0.08
    ä¸įéĹ´
    -0.08
    rylic
    -0.08
    etus
    -0.08
    POSITIVE LOGITS
     slippery
    0.15
     Slip
    0.11
     slip
    0.09
    /slick
    0.09
     slipping
    0.09
     اÙĦسÙĦ
    0.09
     Quentin
    0.09
    _CHARS
    0.09
    åĬ±å¿Ĺ
    0.09
    uka
    0.08
    Activations Density 0.043%

    No Known Activations