© 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. 23932
    Prev
    Next
    INDEX
    Explanations

    concentration-dependent effects

    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
    kö
    -0.10
    姹
    -0.09
    ossa
    -0.08
    perms
    -0.08
    èijĹä½ľ
    -0.08
    å®°
    -0.08
    æĭį
    -0.08
    YST
    -0.08
    anh
    -0.08
    composite
    -0.08
    POSITIVE LOGITS
    urations
    0.11
    ç½ijå°ıç¼ĸ
    0.10
    æĪ¿è´·
    0.10
    解æĶ¾åĨĽ
    0.10
    oodle
    0.10
    ally
    0.09
    梯
    0.09
    çĪ±å°Ķ
    0.09
    ality
    0.09
    ninger
    0.09
    Activations Density 0.101%

    No Known Activations