© 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. 150265
    Prev
    Next
    INDEX
    Explanations

    Sl

    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
    gener
    -0.26
     restraining
    -0.26
     discrimin
    -0.25
    dream
    -0.24
    gressor
    -0.24
    ä¸įç¦ģ
    -0.24
     Gir
    -0.23
     openly
    -0.23
    obili
    -0.23
    å°ıåĦ¿
    -0.23
    POSITIVE LOGITS
    ariat
    0.30
    æĿ¡
    0.27
    isque
    0.27
    _spacing
    0.26
    è´£
    0.26
    än
    0.26
    adden
    0.25
    ution
    0.24
    åĬŀæ¡Ī
    0.24
     GetName
    0.24
    Activations Density 0.865%

    No Known Activations