© 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. 50029
    Prev
    Next
    INDEX
    Explanations

    CF, VF, GF, SF, WF, FF prefixes

    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
    agram
    -0.09
    ächt
    -0.09
    een
    -0.09
    åIJįæł¡
    -0.09
    éıĸ
    -0.09
    _UNDEF
    -0.09
    è®®äºĭ
    -0.08
    åįģåĪĨéĴŁ
    -0.08
    lace
    -0.08
    ãĥģãĤ§
    -0.08
    POSITIVE LOGITS
    razier
    0.10
    ishing
    0.10
    ished
    0.10
    urry
    0.09
    ocused
    0.09
    leur
    0.09
    åIJĮæĥħ
    0.09
    ä¹į
    0.09
    Buzz
    0.09
    å±Ģ
    0.09
    Activations Density 0.234%

    No Known Activations