© 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. 33098
    Prev
    Next
    INDEX
    Explanations

    sound advice or development

    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
    -fw
    -0.09
    0
    -0.09
    ogle
    -0.08
    ya
    -0.08
    quam
    -0.08
    1
    -0.08
    2
    -0.08
    구
    -0.08
    Ãłng
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    NESS
    0.11
    ness
    0.11
    æ¹Ľ
    0.10
    tracked
    0.10
    bite
    0.10
    zza
    0.10
    å½»
    0.10
     discretion
    0.10
    alsa
    0.10
    çĤ¸å¼¹
    0.10
    Activations Density 0.028%

    No Known Activations