© 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. 30602
    Prev
    Next
    INDEX
    Explanations

    sher followed by specific endings

    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
    -0.11
     thiá»ĥu
    -0.10
    ivity
    -0.10
    gregator
    -0.09
    ted
    -0.09
    è°ı
    -0.09
    upported
    -0.09
    笳
    -0.08
    ively
    -0.08
    urate
    -0.08
    POSITIVE LOGITS
    ../../../
    0.13
    idan
    0.10
    eger
    0.10
    reds
    0.10
    é¹ķ
    0.09
    compass
    0.09
    trak
    0.09
    athing
    0.09
    æŁľåı°
    0.09
    .itemView
    0.09
    Activations Density 0.017%

    No Known Activations