© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    developmental and characteristic descriptions

    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
    åıĺåİĭ
    -0.08
    è°£è¨Ģ
    -0.08
    æ·ĺ
    -0.08
    æĢ»æĺ¯
    -0.08
    ä¿ĥæĪIJ
    -0.08
    蹦
    -0.08
    æĹłæĥħ
    -0.08
    åij¼å£°
    -0.08
    è²Į
    -0.08
    ABL
    -0.07
    POSITIVE LOGITS
    eld
    0.10
    isd
    0.10
    éĥijéĩį
    0.10
    elda
    0.10
    ally
    0.10
    ALLY
    0.09
    ional
    0.09
    afil
    0.09
    uide
    0.09
    pard
    0.09
    Activations Density 0.138%

    No Known Activations