© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35165
    Prev
    Next
    INDEX
    Explanations

    ssh key-based authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    ãĥ¼ãĤ¸
    -0.11
    kos
    -0.10
    åIJī祥
    -0.10
    èįī
    -0.09
    olean
    -0.09
    ä¿¡å¿ĥ
    -0.09
    æĸ°åĮº
    -0.09
    urga
    -0.09
    _undo
    -0.08
    çľĭå¾ħ
    -0.08
    POSITIVE LOGITS
    SSH
    0.09
     ssh
    0.09
     SSH
    0.09
    æķ¦
    0.09
    æ°ij宿
    0.09
    ssh
    0.08
    çķĻ
    0.08
    _ssh
    0.08
    ä¸Ńä»ĭ
    0.08
    QUIT
    0.08
    Activations Density 0.177%

    No Known Activations