© 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. 35553
    Prev
    Next
    INDEX
    Explanations

    cargo cults

    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
    cripts
    -0.10
    bah
    -0.09
    ÑĦÑĢ
    -0.09
    mel
    -0.09
    agna
    -0.09
    oft
    -0.09
    Ltd
    -0.09
    ÑĢиÑģ
    -0.09
    kart
    -0.08
    atura
    -0.08
    POSITIVE LOGITS
    ÂĢÂĻ
    0.12
    ness
    0.11
    âĤ¬âĦ¢
    0.10
    侧ç»ĵæŀĦæĢ§
    0.09
    sWith
    0.09
    ÂĢÂ
    0.09
    å·¥å§Ķ
    0.09
    åĿIJèIJ½
    0.08
    èķĪ
    0.08
    åij¦
    0.08
    Activations Density 0.052%

    No Known Activations