© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    php-ids

    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
    änger
    -0.10
     ведÑĮ
    -0.10
    obuf
    -0.09
    anza
    -0.09
    apid
    -0.09
    ipy
    -0.09
    WithPath
    -0.09
    andard
    -0.09
    Placement
    -0.08
    ìľ¨
    -0.08
    POSITIVE LOGITS
    brew
    0.10
    åŁķ
    0.09
    pter
    0.09
    _SELF
    0.09
    ernet
    0.09
    ?option
    0.09
    acter
    0.09
    soever
    0.09
    ded
    0.09
    éĶŃ
    0.09
    Activations Density 0.142%

    No Known Activations