© 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. 48690
    Prev
    Next
    INDEX
    Explanations

    amphitheatre, arboretum, escarpment, promenade

    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
    æĪļ
    -0.10
    ingly
    -0.09
     Jad
    -0.09
    çķ¥
    -0.09
    tre
    -0.08
     setC
    -0.08
    Tre
    -0.08
    åĽº
    -0.08
    éķ¿è¿ľ
    -0.08
    _ca
    -0.08
    POSITIVE LOGITS
    çİŁ
    0.09
    æĺŁåħī
    0.09
    earer
    0.09
    èĭįçĻ½
    0.09
    atsu
    0.08
    aura
    0.08
    èĩĬ
    0.08
    uteur
    0.08
     spontaneously
    0.08
    è°³
    0.08
    Activations Density 0.001%

    No Known Activations