© 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. 149604
    Prev
    Next
    INDEX
    Explanations

    unusual characters and code

    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
     Suites
    -0.30
    /Delete
    -0.27
    ause
    -0.27
    ãĥ¡ãĥ³ãĥĪ
    -0.25
     Suite
    -0.25
     bat
    -0.25
     Pause
    -0.25
    ç»ī
    -0.24
    >Returns
    -0.24
    *)&
    -0.24
    POSITIVE LOGITS
    åı¯æĮģç»Ń
    0.26
    çīĩ
    0.26
    è¾ĵäºĨ
    0.25
    綦
    0.25
    éĿĵ
    0.25
    æĪijåĴĮ
    0.24
    duct
    0.23
    ród
    0.23
    ä¸ľè¥¿
    0.23
    ducted
    0.23
    Activations Density 0.124%

    No Known Activations