© 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. 5763
    Prev
    Next
    INDEX
    Explanations

    classify, string, path

    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
    resses
    -0.09
    gether
    -0.09
     Reflex
    -0.09
     classical
    -0.09
    çŀŃ
    -0.09
    çĶŁæĢķ
    -0.09
    thic
    -0.08
    enders
    -0.08
    wards
    -0.08
    èĥ
    -0.08
    POSITIVE LOGITS
    åĪ«çļĦ
    0.15
    mate
    0.15
    mates
    0.13
    ifying
    0.12
    room
    0.12
    иÑĦика
    0.12
    ify
    0.12
    ë³Ħ
    0.12
    ifications
    0.11
    ical
    0.11
    Activations Density 0.163%

    No Known Activations