© 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. 47776
    Prev
    Next
    INDEX
    Explanations

    ice melting or breaking

    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
    åĿ³
    -0.09
    æݸ
    -0.09
    éħ±
    -0.09
    hra
    -0.09
    nt
    -0.09
    磫
    -0.09
    工夫
    -0.09
    æī³
    -0.09
    è±³
    -0.08
    idar
    -0.08
    POSITIVE LOGITS
    Thickness
    0.09
     Bened
    0.09
    æĭ¯
    0.09
    iola
    0.08
    ERVE
    0.08
    Explorer
    0.08
     Trials
    0.08
    åİļ度
    0.08
    UV
    0.08
    ivic
    0.08
    Activations Density 0.015%

    No Known Activations