© 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. 62072
    Prev
    Next
    INDEX
    Explanations

    camping trips

    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
    edImage
    -0.11
    isches
    -0.10
    onium
    -0.10
     Anast
    -0.10
    éĵĬ
    -0.09
    uale
    -0.09
    amiento
    -0.09
    çīĪæĿĥ
    -0.09
    Copyright
    -0.08
    ursday
    -0.08
    POSITIVE LOGITS
    agn
    0.10
    çĶ¨åĵģ
    0.09
    å¸IJ篷
    0.09
    éľ²
    0.08
    anto
    0.08
    ÑģÑĤÑĢа
    0.08
    unic
    0.08
    uration
    0.08
     verst
    0.08
    eger
    0.08
    Activations Density 0.007%

    No Known Activations