© 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. 25521
    Prev
    Next
    INDEX
    Explanations

    threshold

    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
     ASS
    -0.10
    ija
    -0.10
     TIM
    -0.09
    fest
    -0.09
     Tok
    -0.09
    arto
    -0.09
    lit
    -0.08
    <|fim_suffix|>
    -0.08
    opher
    -0.08
     Ober
    -0.08
    POSITIVE LOGITS
    ed
    0.12
    -library
    0.12
    ing
    0.12
    edImage
    0.11
    olta
    0.11
    -setting
    0.10
    yms
    0.10
    ords
    0.10
    edis
    0.10
    ед
    0.10
    Activations Density 0.003%

    No Known Activations