© 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. 29889
    Prev
    Next
    INDEX
    Explanations

    having a hard time

    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
     Heading
    -0.08
     Mist
    -0.08
    jam
    -0.07
    atham
    -0.07
     Perf
    -0.07
    eye
    -0.07
     Sa
    -0.07
     Abs
    -0.07
     décou
    -0.06
     Inst
    -0.06
    POSITIVE LOGITS
     finding
    0.14
     difficulty
    0.14
    /cop
    0.13
     trouble
    0.12
     locating
    0.11
     بÙĩ
    0.11
     time
    0.11
     Eck
    0.11
     chance
    0.11
     convincing
    0.11
    Activations Density 0.026%

    No Known Activations