© 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. 62133
    Prev
    Next
    INDEX
    Explanations

    broad range/array/aims

    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
    utter
    -0.09
    çĭIJ
    -0.09
    ERY
    -0.09
    è¿ĩé«ĺ
    -0.09
    窮
    -0.09
    apo
    -0.08
    andel
    -0.08
    sek
    -0.08
    ision
    -0.08
    æİīäºĨ
    -0.08
    POSITIVE LOGITS
    ening
    0.16
     rãi
    0.15
    ened
    0.14
    .TryParse
    0.12
    loom
    0.11
    est
    0.11
    è§Ĩéĩİ
    0.11
    leaf
    0.11
    -minded
    0.11
    èĥ¸æĢĢ
    0.10
    Activations Density 0.067%

    No Known Activations