© 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. 11588
    Prev
    Next
    INDEX
    Explanations

    ferry terminals and boats

    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
    ally
    -0.09
     shrinking
    -0.08
    _ENCODING
    -0.08
    åŁŁ
    -0.08
    nt
    -0.08
    ALLY
    -0.08
    lo
    -0.08
    راب
    -0.08
    ness
    -0.08
    ALE
    -0.08
    POSITIVE LOGITS
    boards
    0.09
    quam
    0.09
    jen
    0.09
    BIND
    0.09
    ç¾¤å²Ľ
    0.09
    åĵį
    0.09
    hall
    0.09
    åı¸
    0.09
    pike
    0.08
    ä¸ĭè¡Į
    0.08
    Activations Density 0.003%

    No Known Activations