© 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. 32607
    Prev
    Next
    INDEX
    Explanations

    cat

    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
    edy
    -0.11
    ingly
    -0.10
    etta
    -0.10
    abad
    -0.09
    aid
    -0.09
    edList
    -0.09
    tics
    -0.09
    edic
    -0.09
    eta
    -0.09
    affer
    -0.09
    POSITIVE LOGITS
    apult
    0.13
    nip
    0.12
    iced
    0.11
    égorie
    0.10
    mans
    0.10
    onical
    0.10
    enary
    0.09
    /cat
    0.09
    liqu
    0.09
    alysis
    0.09
    Activations Density 0.015%

    No Known Activations