© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53254
    Prev
    Next
    INDEX
    Explanations

    like you or yours

    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
    èĽĬ
    -0.09
    åĦ¿å¥³
    -0.08
    水管
    -0.08
    éĶ²
    -0.08
     Mast
    -0.08
    _footer
    -0.08
    anging
    -0.08
    ugging
    -0.08
    è¶Ĭ
    -0.07
    ä¸ĬéŨ
    -0.07
    POSITIVE LOGITS
    åĥı
    0.25
     like
    0.23
     Like
    0.18
    like
    0.16
    Like
    0.16
    å¦Ĥ
    0.16
    .like
    0.15
     LIKE
    0.15
     nhÆ°
    0.14
     seperti
    0.14
    Activations Density 0.089%

    No Known Activations