© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    AT&T

    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
    While
    -0.12
     Throughout
    -0.12
    SDK
    -0.12
    Throughout
    -0.12
    Once
    -0.11
     While
    -0.11
     As
    -0.11
     It
    -0.11
     Although
    -0.11
    Though
    -0.11
    POSITIVE LOGITS
     Regards
    0.08
    InstanceOf
    0.07
    <|endoftext|>
    0.07
    Ùī
    0.07
     //////////////////////////////////////////////////////////////////////
    0.07
     UL
    0.07
     ctl
    0.07
    çīĩ
    0.07
     spor
    0.07
     ASS
    0.07
    Activations Density 0.029%

    No Known Activations