© 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. 52656
    Prev
    Next
    INDEX
    Explanations

    fields in customer forms

    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
    addir
    -0.09
    èĮĢ
    -0.09
    _REPLY
    -0.09
    張貼
    -0.08
    æ²īé»ĺ
    -0.08
    usercontent
    -0.08
    .setOutput
    -0.08
    éĥ¦
    -0.08
    驾
    -0.08
    iri
    -0.08
    POSITIVE LOGITS
    订åįķ
    0.10
    ä¸ĭåįķ
    0.10
    ç¯Ļ
    0.10
    å¤ĸè´¸
    0.10
    åĶ®åIJİ
    0.09
    è´Ńçī©
    0.09
    åıijè´§
    0.09
    龸çİĭ
    0.09
    åĨ²åĬ¨
    0.08
    çķĻè¨Ģ
    0.08
    Activations Density 0.122%

    No Known Activations