© 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. 63343
    Prev
    Next
    INDEX
    Explanations

    Leroy, Lerchen, Dorsey, Konduit

    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
    nement
    -0.10
    eer
    -0.10
    auc
    -0.10
    aus
    -0.10
    ãĤĭ
    -0.09
    iams
    -0.09
    ãĥ³ãĤ°
    -0.09
    ing
    -0.09
    çĸĹæ³ķ
    -0.09
    ein
    -0.08
    POSITIVE LOGITS
    Ùij
    0.13
    ê¹IJ
    0.12
    sters
    0.10
    rone
    0.10
    èĩ¾
    0.09
    teen
    0.09
    ëį°
    0.09
    å±ŀäºİ
    0.08
    ä¸ľè¥¿
    0.08
    ereal
    0.08
    Activations Density 0.828%

    No Known Activations