© 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. 61173
    Prev
    Next
    INDEX
    Explanations

    seahaven

    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
    entially
    -0.11
    er
    -0.10
    icism
    -0.10
    erah
    -0.09
    ewood
    -0.09
    ighbors
    -0.09
    ively
    -0.09
    edException
    -0.09
    uptools
    -0.09
    iéndo
    -0.09
    POSITIVE LOGITS
    oll
    0.11
    elay
    0.11
    ike
    0.10
    0
    0.09
    ave
    0.09
    ollar
    0.09
    aze
    0.09
    ีà¹ī
    0.08
    azer
    0.08
    space
    0.08
    Activations Density 0.739%

    No Known Activations