© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    let's not

    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
    дей
    -0.12
     PSU
    -0.10
    GenerationStrategy
    -0.10
    ERRU
    -0.09
    @update
    -0.09
    éĿ¢èī²
    -0.09
    ROTO
    -0.09
    uity
    -0.09
    CallableWrapper
    -0.09
    åĽĽåij¨
    -0.09
    POSITIVE LOGITS
    æĢİä¹Ī说
    0.10
    ede
    0.09
    è¿ijè·Ŀ离
    0.09
    å§ij
    0.09
     Brit
    0.09
    ä¸į让
    0.09
    anth
    0.08
     Lun
    0.08
    ä¸įæİĴéĻ¤
    0.08
    帽
    0.08
    Activations Density 0.022%

    No Known Activations