© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37427
    Prev
    Next
    INDEX
    Explanations

    ladder

    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
    æĢ¿
    -0.09
    моÑĢ
    -0.09
    è°Ł
    -0.09
    Maker
    -0.09
    è¿ľç¦»
    -0.09
    æ·±å±Ĥ
    -0.08
    zon
    -0.08
    æł¸å¿ĥåĮº
    -0.08
    éļĶçĿĢ
    -0.08
    nom
    -0.08
    POSITIVE LOGITS
    æĶĢçĻ»
    0.13
    æłijæŀĿ
    0.12
     ladder
    0.11
    æŀĿ
    0.11
    æijĺ
    0.11
    çĪ¬ä¸Ĭ
    0.10
    æĶĢ
    0.10
    _BRANCH
    0.10
    çĻ»ä¸Ĭ
    0.10
     plank
    0.10
    Activations Density 0.068%

    No Known Activations