© 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. 30184
    Prev
    Next
    INDEX
    Explanations

    cancel, cancelled, cancellation

    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
    åĺ´å·´
    -0.11
    ãĥĥãĤ·ãĥ¥
    -0.10
    æĴº
    -0.10
    ELL
    -0.09
    shed
    -0.09
    åĵĩ
    -0.09
    lessness
    -0.09
    åŃĺéĩı
    -0.09
    croft
    -0.09
    Clr
    -0.08
    POSITIVE LOGITS
    äºĨåĩł
    0.10
    ãģļãģ«
    0.10
    AnimationFrame
    0.09
    lob
    0.09
    tered
    0.09
    otta
    0.09
    äºĨ许å¤ļ
    0.09
    äºĨä»ĸçļĦ
    0.09
    ãģ¨è¨Ģãģ£ãģ¦
    0.09
    çĬĢ
    0.09
    Activations Density 0.010%

    No Known Activations