© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115470
    Prev
    Next
    INDEX
    Explanations

    Timothy names

    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
    @js
    -0.11
    uste
    -0.09
    _SB
    -0.09
     Attr
    -0.09
     concession
    -0.09
    á»įn
    -0.09
     domic
    -0.08
    ENU
    -0.08
    ails
    -0.08
    AILS
    -0.08
    POSITIVE LOGITS
     tim
    0.16
     Tim
    0.15
    Tim
    0.13
    (TIM
    0.12
     TIM
    0.11
     timp
    0.10
    tim
    0.10
    _TIM
    0.10
    _tim
    0.09
    TIM
    0.09
    Activations Density 0.080%

    No Known Activations