© 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. 36357
    Prev
    Next
    INDEX
    Explanations

    waiting for

    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
    ÖĦ
    -0.09
    æ³ķå¾ĭ顾éĹ®
    -0.09
    工信éĥ¨
    -0.09
     вне
    -0.09
    _OPCODE
    -0.09
    æĢ»ç®Ĺ
    -0.09
    éĺ¡
    -0.09
    éķĬ
    -0.09
    èļ§
    -0.09
    \Module
    -0.09
    POSITIVE LOGITS
    çŃīå¾ħ
    0.23
    çŃīçĿĢ
    0.21
    çŃīåĢĻ
    0.21
     waiting
    0.18
     Waiting
    0.17
    waiting
    0.17
    Waiting
    0.16
     ожида
    0.15
    å¾ħãģ¡
    0.15
     wait
    0.15
    Activations Density 0.063%

    No Known Activations