© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36875
    Prev
    Next
    INDEX
    Explanations

    parole and probation matters

    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
    _pod
    -0.09
    ule
    -0.09
    thur
    -0.08
    pod
    -0.08
    gence
    -0.08
    irm
    -0.08
    blocking
    -0.08
    Ø´Ùħ
    -0.08
     pod
    -0.08
    iture
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.13
    æľŁéĸĵ
    0.11
    reso
    0.09
    å³Ļ
    0.09
    ìį¨
    0.09
    æĹĥ
    0.09
    ëįķ
    0.09
    æľŁåĨħ
    0.09
    以æĿ¥
    0.09
    åľ¨å®¶
    0.09
    Activations Density 0.005%

    No Known Activations