© 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. 53556
    Prev
    Next
    INDEX
    Explanations

    salt and salinity

    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
    è´¢åĬĽ
    -0.10
    æ£į
    -0.09
    å®Ľ
    -0.09
    odor
    -0.09
    éĽģ
    -0.09
    IMS
    -0.08
    å°¢
    -0.08
    èĭŁ
    -0.08
    went
    -0.08
    管å±Ģ
    -0.08
    POSITIVE LOGITS
    åĴ¸
    0.10
    salt
    0.09
    çŃ
    0.09
     Blink
    0.09
    模ç³Ĭ
    0.09
     Salt
    0.09
    éģ¥
    0.09
    çĽIJ
    0.09
     Overrides
    0.08
    Ø°
    0.08
    Activations Density 0.057%

    No Known Activations