© 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. 19263
    Prev
    Next
    INDEX
    Explanations

    caliber, gauge, quality, size

    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
    æĭį
    -0.10
    uces
    -0.09
     glorious
    -0.09
    yb
    -0.08
    ราว
    -0.08
    edom
    -0.08
    åĨĬ
    -0.08
    ery
    -0.08
    odore
    -0.08
    å½ĵå±Ģ
    -0.08
    POSITIVE LOGITS
    theless
    0.11
    åĨħçļĦ
    0.10
    åıijå±ķ空éĹ´
    0.10
    ıyla
    0.10
    æľīä¿¡å¿ĥ
    0.10
    WISE
    0.10
    ately
    0.10
    åıijå±ķéĺ¶æ®µ
    0.09
    åī¯ä¸»ä»»
    0.09
    ity
    0.09
    Activations Density 0.005%

    No Known Activations