© 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. 33082
    Prev
    Next
    INDEX
    Explanations

    super/suprem/suppl

    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
    uate
    -0.11
     PIT
    -0.10
    otomy
    -0.10
    scopes
    -0.09
    CriticalSection
    -0.09
    èĿł
    -0.09
    å²ĸ
    -0.08
     ÑĥÑģпеÑħ
    -0.08
    umph
    -0.08
     muj
    -0.08
    POSITIVE LOGITS
    antha
    0.13
    pliers
    0.12
    indle
    0.12
    ervised
    0.12
    ervisor
    0.11
    plied
    0.11
    plies
    0.10
    plement
    0.10
    ra
    0.10
    erto
    0.10
    Activations Density 0.070%

    No Known Activations