© 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. 30086
    Prev
    Next
    INDEX
    Explanations

    This is adjective/determiner

    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
     PACKET
    -0.10
    樯
    -0.09
    umm
    -0.09
     каÑĩ
    -0.09
    åĪĽæĸ°åıijå±ķ
    -0.09
    å»ī
    -0.08
    羣æĥħ
    -0.08
    Ÿ
    -0.08
    éĿ
    -0.08
    ç·
    -0.08
    POSITIVE LOGITS
    ihil
    0.09
    tmpl
    0.09
    ç®Ĺæĺ¯
    0.09
    iali
    0.09
     Heath
    0.08
    ÑıÑħ
    0.08
    è¨Ģ论
    0.08
    sse
    0.08
    iable
    0.08
    è¿ĩå¾Ĺ
    0.08
    Activations Density 0.072%

    No Known Activations