© 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. 50944
    Prev
    Next
    INDEX
    Explanations

    sign up for

    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
    ParameterValue
    -0.10
    inct
    -0.10
    aceous
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    æ²Ļ
    -0.09
    ä¾ĭè¡Į
    -0.09
     Fritz
    -0.09
    Parcelable
    -0.09
    IVEN
    -0.08
    unos
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.09
    éĵĮ
    0.09
     for
    0.09
    èĪ«
    0.08
    åıĤåĬł
    0.08
     ridge
    0.08
    acco
    0.08
     ÑĢаÑģÑģмаÑĤÑĢ
    0.08
    RC
    0.08
    å°ijè§ģ
    0.08
    Activations Density 0.003%

    No Known Activations