© 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. 49901
    Prev
    Next
    INDEX
    Explanations

    pathfinding algorithms and graph traversal

    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
    eller
    -0.08
    orough
    -0.08
    çĮľ
    -0.08
    quat
    -0.08
    åģļ大
    -0.08
    辨åĪ«
    -0.07
    Guess
    -0.07
     gest
    -0.07
    è¤
    -0.07
     Twins
    -0.07
    POSITIVE LOGITS
     маÑĢÑĪ
    0.11
    è·¯å¾Ħ
    0.10
     paths
    0.10
    èµ°å¾Ĺ
    0.10
    /path
    0.10
    çĸıæķ£
    0.10
    ijkstra
    0.10
    è·¯
    0.10
    _paths
    0.10
     Paths
    0.10
    Activations Density 0.113%

    No Known Activations