© 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. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108131
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odal
    -0.28
    åħ¶æīĢ
    -0.28
    çľĭä½ł
    -0.27
    ä¼ļä¸Ĭ
    -0.27
    ä¹ŁæŃ£æĺ¯
    -0.25
    âĢĽ
    -0.25
    lessly
    -0.24
    GetObject
    -0.24
    åīįèĢħ
    -0.24
    ably
    -0.24
    POSITIVE LOGITS
    æľīäºĽ
    0.31
    å¤ļãģıãģ®
    0.29
    å¾Īå¤ļ
    0.28
    èĸľ
    0.28
    éĥ½å¾Ī
    0.27
    papers
    0.27
    éĤ¶
    0.27
     papers
    0.26
    çļĦä¸ĢäºĽ
    0.26
     scri
    0.25
    Activations Density 0.912%

    No Known Activations