© 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. 9693
    Prev
    Next
    INDEX
    Explanations

    heck of a, heck do you, hectic news

    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
    è§ī
    -0.09
    nist
    -0.09
    ãĥķãĤ©ãĥ¼
    -0.09
    çģ«çĪĨ
    -0.08
    unar
    -0.08
    yla
    -0.08
    è¡Į车
    -0.08
    ç¿©
    -0.08
    åıijæī¬
    -0.08
    轻微
    -0.08
    POSITIVE LOGITS
    erry
    0.10
    ë¡ł
    0.09
    åİŁæłĩé¢ĺ
    0.09
    imon
    0.09
    ult
    0.08
    èį¦
    0.08
    è¡ĮæĶ¿åĮº
    0.08
    å¾ľ
    0.08
    æľºåħ³
    0.08
    ckt
    0.08
    Activations Density 0.002%

    No Known Activations