© 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. 32226
    Prev
    Next
    INDEX
    Explanations

    never-ending, never-before, never taking, Never Enough

    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
    sWith
    -0.12
    speed
    -0.11
    ively
    -0.11
    annis
    -0.10
    srv
    -0.10
    sp
    -0.10
    sr
    -0.10
    scheduler
    -0.09
    овÑĭй
    -0.09
    erton
    -0.09
    POSITIVE LOGITS
    theless
    0.20
    bies
    0.14
    hood
    0.12
    greens
    0.10
    hall
    0.10
    lich
    0.10
    ocity
    0.10
    lah
    0.09
    thing
    0.09
    thin
    0.09
    Activations Density 0.037%

    No Known Activations