© 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. 38432
    Prev
    Next
    INDEX
    Explanations

    bloating, blokes, blooper, bloomed

    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
    ters
    -0.09
    ication
    -0.09
    è¾Ħ
    -0.09
    éĽ¹
    -0.08
    upal
    -0.08
    åį¦
    -0.08
    å¯Łçľĭ
    -0.08
    ball
    -0.08
    елÑı
    -0.08
    bars
    -0.08
    POSITIVE LOGITS
    itim
    0.11
     Ñģобой
    0.10
    èĩĥ
    0.10
    Ìģ
    0.09
    èĨĺ
    0.09
    iti
    0.09
    åĶı
    0.09
    ÑĪек
    0.08
    æĩij
    0.08
    yped
    0.08
    Activations Density 0.004%

    No Known Activations