© 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. 24-TRANSCODER-HP
    7. 149898
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    临
    -0.33
     https
    -0.31
    https
    -0.31
    å¤ļå¹´
    -0.30
    çĹĽ
    -0.28
     COVID
    -0.28
    æī¹åıij
    -0.27
     minim
    -0.27
     covid
    -0.27
    æķ´ä½ĵ
    -0.27
    POSITIVE LOGITS
    irst
    0.29
     campaigning
    0.26
    Caught
    0.26
    女åŃ©
    0.26
     battleground
    0.25
    ÑģÑĤÑĢоиÑĤелÑĮ
    0.25
     fortunes
    0.25
     catches
    0.25
    åĥ®
    0.24
    æīĢæıIJä¾Ľ
    0.24
    Activations Density 0.032%

    No Known Activations