© 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. 27886
    Prev
    Next
    INDEX
    Explanations

    loads, starts, validates, assigns

    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
    swith
    -0.16
    able
    -0.15
    the
    -0.15
    ths
    -0.14
    äºĨä¸Ģ
    -0.14
    äºĨä¸Ģç³»åĪĹ
    -0.13
    ä¸Ģç§į
    -0.13
    they
    -0.13
    that
    -0.13
    ä¸ĢäºĽ
    -0.13
    POSITIVE LOGITS
    upport
    0.16
    pace
    0.16
    cheme
    0.16
    heet
    0.15
    uite
    0.15
    ervice
    0.15
    ervices
    0.14
    ymbol
    0.14
    chema
    0.14
    /rem
    0.14
    Activations Density 0.795%

    No Known Activations