© 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. 114760
    Prev
    Next
    INDEX
    Explanations

    I cannot

    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
     unnecessary
    -0.10
     redund
    -0.09
     seemed
    -0.09
     nobody
    -0.09
     Hij
    -0.09
    /tests
    -0.09
     Disconnect
    -0.09
    undle
    -0.09
     tended
    -0.09
     ICMP
    -0.09
    POSITIVE LOGITS
     cannot
    0.22
    cannot
    0.19
    ä¸įèĥ½
    0.18
     Cannot
    0.18
    Cannot
    0.18
     couldn
    0.15
     cant
    0.15
    ä¸įèĥ½ä¸ºç©º
    0.14
     refuse
    0.14
     imposs
    0.12
    Activations Density 0.069%

    No Known Activations