© 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. 149866
    Prev
    Next
    INDEX
    Explanations

    want

    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
    isten
    -0.27
    迹
    -0.27
     absorbing
    -0.25
     accurate
    -0.24
     niche
    -0.23
    ãĤĭãģ¨
    -0.23
    精确
    -0.23
     dece
    -0.23
    igung
    -0.23
    _beam
    -0.23
    POSITIVE LOGITS
     pud
    0.25
    åł°
    0.25
    ç¦Ģ
    0.25
     示
    0.23
    NotAllowed
    0.23
    aign
    0.23
    æģ©æĸ½
    0.23
     Strap
    0.23
     others
    0.23
     PLAY
    0.23
    Activations Density 0.149%

    No Known Activations