© 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. 22117
    Prev
    Next
    INDEX
    Explanations

    ? Set

    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
    ä¹Łéĥ½
    -0.12
    ä¹Łå¸ĮæľĽ
    -0.12
    ä½Ĩä»ĸ们
    -0.12
    äºĨä»ĸçļĦ
    -0.12
    沤
    -0.11
    åĪ©äºļ
    -0.11
    è°Ĺ
    -0.11
    èĩĥ
    -0.10
    berman
    -0.10
    ä½Ĩä»ĸ
    -0.10
    POSITIVE LOGITS
    1
    0.11
    2
    0.10
    3
    0.10
    0
    0.10
    8
    0.10
    7
    0.10
    6
    0.10
    9
    0.10
    4
    0.09
    èĻ½çĦ¶
    0.09
    Activations Density 0.332%

    No Known Activations