© 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. 16527
    Prev
    Next
    INDEX
    Explanations

    returning home

    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
     afterwards
    -0.10
     elsewhere
    -0.09
     Afterwards
    -0.08
     defe
    -0.08
     disappear
    -0.08
    ulg
    -0.07
     Recovery
    -0.07
     liber
    -0.07
     absor
    -0.07
     dismant
    -0.07
    POSITIVE LOGITS
     RETURN
    0.14
     returned
    0.13
     returning
    0.12
     kino
    0.12
     return
    0.12
    	return
    0.11
     Returning
    0.11
     returns
    0.11
    ")+
    0.11
    anker
    0.11
    Activations Density 0.099%

    No Known Activations