© 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. 6892
    Prev
    Next
    INDEX
    Explanations

    ecological functions, services, success, damage

    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
    acts
    -0.09
    akk
    -0.08
    ably
    -0.08
    麻çĹ¹
    -0.08
    age
    -0.08
    è§Ħå®ļ
    -0.08
    ucc
    -0.08
     phép
    -0.08
    est
    -0.08
    urg
    -0.08
    POSITIVE LOGITS
    /ec
    0.12
     minded
    0.11
    çĤŃ
    0.11
    ISTS
    0.10
    carbon
    0.10
    ALLY
    0.09
    iful
    0.09
    平衡
    0.09
    -minded
    0.09
    OTHER
    0.09
    Activations Density 0.010%

    No Known Activations