© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    external declaration or keyword

    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
    łéĻ¤
    -0.14
    DED
    -0.10
    -pencil
    -0.10
    )did
    -0.09
    OfString
    -0.09
    äge
    -0.09
    ¡°
    -0.09
    =User
    -0.09
    .wp
    -0.09
    /he
    -0.09
    POSITIVE LOGITS
    <|fim_middle|>
    0.07
    onga
    0.07
    525
    0.05
    809
    0.05
    abort
    0.05
    ören
    0.05
    idor
    0.05
    995
    0.05
    rect
    0.05
    ovah
    0.05
    Activations Density 15.471%

    No Known Activations