© 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. 150510
    Prev
    Next
    INDEX
    Explanations

    Code snippets and math

    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
    ä¸Ģè§Ī
    -0.27
     Model
    -0.27
     Fri
    -0.26
    .IntPtr
    -0.25
    irsch
    -0.25
    æ¾ľ
    -0.25
    pri
    -0.25
    searchModel
    -0.25
    =tf
    -0.25
     Rim
    -0.25
    POSITIVE LOGITS
    -default
    0.27
    è¡į
    0.27
    èĪį
    0.27
    rale
    0.27
    -dd
    0.26
    çīºçī²
    0.26
     sup
    0.26
    udos
    0.25
    ubbo
    0.25
     cloning
    0.25
    Activations Density 0.165%

    No Known Activations