© 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. 61641
    Prev
    Next
    INDEX
    Explanations

    handling individual components

    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
    INA
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    åĶ¯
    -0.08
    è¤Ĭ
    -0.08
    aci
    -0.08
    åħīåѦ
    -0.08
    ç±į
    -0.08
    -
    -0.08
    çļĦä¸ľè¥¿
    -0.07
    ertainment
    -0.07
    POSITIVE LOGITS
     individual
    0.14
     einzel
    0.14
    individual
    0.12
    Individual
    0.11
     конкÑĢеÑĤ
    0.11
     Individual
    0.11
    çľģ份
    0.10
    个èĤ¡
    0.10
    çļĦåħ·ä½ĵ
    0.10
    åħ·ä½ĵçļĦ
    0.10
    Activations Density 0.077%

    No Known Activations