© 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. 150753
    Prev
    Next
    INDEX
    Explanations

    Olympics

    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
    æ®ĸ
    -0.28
    OSC
    -0.27
    IFIER
    -0.27
    çľ·
    -0.27
    éĻī
    -0.26
    éĥ¨éķ¿
    -0.26
    cntl
    -0.26
     rose
    -0.24
     charms
    -0.24
    asks
    -0.24
    POSITIVE LOGITS
    æĶ¸
    0.29
    DDL
    0.28
     ÑĥнивеÑĢÑģиÑĤеÑĤ
    0.27
    yo
    0.26
     Helm
    0.25
    ship
    0.24
    MV
    0.24
    anford
    0.24
    èĭĽ
    0.24
    jas
    0.23
    Activations Density 0.060%

    No Known Activations