© 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. 35154
    Prev
    Next
    INDEX
    Explanations

    fonts or completion

    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
    åĸľæĤ¦
    -0.10
    åīį沿
    -0.09
    StackSize
    -0.09
    æĸĽ
    -0.09
    çĺŁ
    -0.08
    istani
    -0.08
    æı´
    -0.08
    就好åĥı
    -0.08
    塬
    -0.08
    .Len
    -0.08
    POSITIVE LOGITS
    ields
    0.11
    uen
    0.09
    perse
    0.09
    fulness
    0.09
    andle
    0.08
    _RM
    0.08
    LETTE
    0.08
    FUL
    0.08
    andex
    0.08
    è¿Ļ个æŶåĢĻ
    0.08
    Activations Density 0.400%

    No Known Activations