© 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. 55801
    Prev
    Next
    INDEX
    Explanations

    catch or catch up

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    ized
    -0.10
    icient
    -0.09
    å§Ķ书记
    -0.09
    illy
    -0.09
    íıIJ
    -0.09
    strup
    -0.09
    änd
    -0.08
    견
    -0.08
    tha
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.11
    timeofday
    0.10
    phrase
    0.09
    ey
    0.09
    AndUpdate
    0.09
    annel
    0.09
    roph
    0.09
    ä¸įä»ħå¦ĤæѤ
    0.09
    ouri
    0.09
    scape
    0.09
    Activations Density 0.025%

    No Known Activations