© 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. 11404
    Prev
    Next
    INDEX
    Explanations

    label and definition

    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
    lander
    -0.11
    nish
    -0.09
    nage
    -0.09
    elige
    -0.09
    ality
    -0.09
    é¼IJ
    -0.08
    /her
    -0.08
    reb
    -0.08
    lish
    -0.08
    land
    -0.08
    POSITIVE LOGITS
    NewLabel
    0.13
    ings
    0.13
     nameLabel
    0.12
    ä¸įæ¸ħ
    0.12
    lama
    0.10
    =label
    0.10
    GED
    0.10
    è´¢æĶ¿éĥ¨
    0.10
     htmlFor
    0.10
    legate
    0.09
    Activations Density 0.042%

    No Known Activations