© 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. 10560
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    åĬŁåĬĽ
    -0.09
    ä¸Ģå¤Ħ
    -0.09
    unct
    -0.08
    ibal
    -0.08
    Scoped
    -0.08
    GED
    -0.08
    è¿ĩäºĨ
    -0.08
    ä¸ĢèĤ¡
    -0.08
    _fa
    -0.08
    Nib
    -0.08
    POSITIVE LOGITS
    .hot
    0.09
    èĨº
    0.09
     prosec
    0.09
    ä¸įæĩĪ
    0.09
     Dess
    0.08
    çĶ³
    0.08
    illery
    0.08
    親
    0.07
     JM
    0.07
    detach
    0.07
    Activations Density 0.016%

    No Known Activations