© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37680
    Prev
    Next
    INDEX
    Explanations

    selfies and up

    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
    çijĻ
    -0.09
    以éĺ²
    -0.09
    ız
    -0.09
    å®Įæķ´çļĦ
    -0.09
    _shortcode
    -0.09
    sdale
    -0.09
    ä¸Ģè¶Ł
    -0.09
    chestra
    -0.08
    åIJĦæł·
    -0.08
     ani
    -0.08
    POSITIVE LOGITS
    ðŁı¼
    0.12
    ðŁı½
    0.10
    ðŁı»
    0.10
    .sdk
    0.09
    ðŁı¾
    0.08
    çĥ¬
    0.08
     batt
    0.08
    æı®
    0.08
    ging
    0.08
    åij½è¿IJ
    0.08
    Activations Density 0.006%

    No Known Activations