© 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. 30607
    Prev
    Next
    INDEX
    Explanations

    Miss followed by a name or title

    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
    åŃ³
    -0.09
    ãģĦãģĨ
    -0.08
    3
    -0.08
    td
    -0.08
    使çĶ¨èĢħ
    -0.08
    4
    -0.08
    6
    -0.08
    5
    -0.08
    ee
    -0.08
    ÙĪØ´
    -0.08
    POSITIVE LOGITS
    issippi
    0.13
    ouri
    0.10
    usion
    0.10
    aldi
    0.10
    ended
    0.10
    ÂŃing
    0.09
    ÙĤار
    0.09
    miss
    0.09
    enser
    0.09
    endant
    0.09
    Activations Density 0.011%

    No Known Activations