© 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. 62482
    Prev
    Next
    INDEX
    Explanations

    state-based, state processing

    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
    æŨ
    -0.10
    Ñĩик
    -0.09
    æıŃ示
    -0.09
    æľĢå¤ļ
    -0.09
    igne
    -0.09
    ycin
    -0.08
    èĮĥåĽ´åĨħ
    -0.08
    Ñģад
    -0.08
    -born
    -0.08
    arine
    -0.08
    POSITIVE LOGITS
     state
    0.20
    çĬ¶æĢģ
    0.18
    state
    0.17
     ÑģоÑģÑĤоÑıние
    0.17
    çĭĢæħĭ
    0.15
     newState
    0.14
    (state
    0.14
     states
    0.14
    çļĦçĬ¶æĢģ
    0.14
    StateException
    0.14
    Activations Density 0.151%

    No Known Activations