© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52901
    Prev
    Next
    INDEX
    Explanations

    remote access and control

    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
    POOL
    -0.09
    éĨ
    -0.09
     perman
    -0.08
    å±¥
    -0.08
    åĩºåħ¥
    -0.08
     sandwiches
    -0.08
    æıIJåĩºäºĨ
    -0.08
    esc
    -0.08
    esi
    -0.08
    æ¿¡
    -0.08
    POSITIVE LOGITS
    éģ¥æݧ
    0.16
    (remote
    0.15
    éģ¥è¿ľ
    0.15
    è¿ľç¨ĭ
    0.15
    .Remote
    0.14
    remote
    0.14
    è¿ľå¤Ħ
    0.13
    .remote
    0.12
     Remote
    0.12
    -away
    0.12
    Activations Density 0.105%

    No Known Activations