© 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. 19563
    Prev
    Next
    INDEX
    Explanations

    literary followed by publication types

    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
    buster
    -0.10
    ummer
    -0.10
    ĩ
    -0.08
    silver
    -0.08
    edic
    -0.08
    ward
    -0.08
    å¸Ĥåİ¿
    -0.08
    /of
    -0.08
    NST
    -0.08
     Flux
    -0.08
    POSITIVE LOGITS
    -minded
    0.11
    ifacts
    0.10
    thing
    0.10
    åĩºä¼Ĺ
    0.09
    ischer
    0.09
    zens
    0.09
    ystate
    0.09
    åı²ä¸Ĭ
    0.09
    (DBG
    0.09
    jal
    0.09
    Activations Density 0.004%

    No Known Activations