© 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. 54878
    Prev
    Next
    INDEX
    Explanations

    magnitude of response

    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
    nt
    -0.12
    ï¸ı
    -0.10
    oron
    -0.10
    ï¸
    -0.09
    åľ°çĭ±
    -0.09
    é²į
    -0.09
    éĹ´æİ¥
    -0.09
    arus
    -0.09
    ç«ĭãģ¦
    -0.09
    ONS
    -0.09
    POSITIVE LOGITS
    istic
    0.10
    cy
    0.10
    led
    0.10
    iron
    0.09
    zza
    0.09
    eling
    0.09
    cr
    0.09
    cri
    0.09
    OfWork
    0.09
    gies
    0.09
    Activations Density 0.029%

    No Known Activations