© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22388
    Prev
    Next
    INDEX
    Explanations

    keratin and kernel

    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
    enance
    -0.12
    sWith
    -0.10
     dame
    -0.09
    íĴĪ
    -0.09
    ç«łç¨ĭ
    -0.09
    .clf
    -0.09
    ively
    -0.09
    ieurs
    -0.09
    iator
    -0.08
    eur
    -0.08
    POSITIVE LOGITS
    åľ°å¸¦
    0.11
    rien
    0.10
    èļĢ
    0.09
    beros
    0.09
    ties
    0.09
    aceous
    0.09
    bone
    0.09
    ror
    0.09
    ERE
    0.09
    åĽ½éĻħå¸Ĥåľº
    0.09
    Activations Density 0.025%

    No Known Activations