© 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. 7087
    Prev
    Next
    INDEX
    Explanations

    Pit Bull or pituitary

    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
    èĥº
    -0.09
    uren
    -0.09
    eric
    -0.09
    quila
    -0.08
    å¿ĸ
    -0.08
    strike
    -0.08
    åľŁåľ°
    -0.08
    æ¢ĥ
    -0.08
    idade
    -0.08
    LINE
    -0.08
    POSITIVE LOGITS
    iful
    0.12
    iless
    0.12
    ting
    0.12
    bull
    0.12
     Pit
    0.11
    angent
    0.10
     pit
    0.10
    ãĥ§ãĥ³
    0.09
    åĿij
    0.09
    pit
    0.09
    Activations Density 0.015%

    No Known Activations