© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 2791
    Prev
    Next
    INDEX
    Explanations

    year, month, or day

    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
    å±ĬæĹ¶
    -0.12
    ä½Ĩæĺ¯ä»ĸ
    -0.11
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.10
    åIJ¦åĪĻ
    -0.10
    ä½Ĩä»ĸ
    -0.10
    æ°ĸ
    -0.10
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.10
    è¿Ļ个æĹ¶ä»£
    -0.10
    ä½Ĩå®ĥ
    -0.10
    æīĢ以æĪij
    -0.09
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.11
    OSC
    0.11
    åīĩ
    0.10
    åĪĻ
    0.09
     meanwhile
    0.09
    exclusive
    0.08
    ereo
    0.08
    ниÑĩ
    0.08
    SCRI
    0.08
    ï¼ļ
    0.08
    Activations Density 0.135%

    No Known Activations