© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33512
    Prev
    Next
    INDEX
    Explanations

    absent or nonexistent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     enlarg
    -0.11
    iero
    -0.10
    idd
    -0.10
     enlargement
    -0.10
     Nin
    -0.10
    ocz
    -0.09
    102
    -0.09
     Vish
    -0.09
     fetish
    -0.09
     insan
    -0.08
    POSITIVE LOGITS
     absent
    0.31
     nonexistent
    0.26
     gone
    0.24
     disappeared
    0.23
     vanished
    0.22
    ä¸įåŃĺåľ¨
    0.22
     disappears
    0.21
     disappear
    0.21
     ìĹĨ
    0.20
     vanish
    0.20
    Activations Density 0.597%

    No Known Activations