© 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. 150741
    Prev
    Next
    INDEX
    Explanations

    use

    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
     image
    -0.28
    isz
    -0.26
    image
    -0.25
     Images
    -0.25
     images
    -0.25
    loomberg
    -0.24
     cast
    -0.24
    Åĵuvre
    -0.24
     quali
    -0.23
    BarItem
    -0.23
    POSITIVE LOGITS
     resources
    0.42
    èµĦæºIJ
    0.39
     Resources
    0.36
    æĻĤéĸĵãģĮ
    0.33
    resources
    0.32
     вÑĢемени
    0.32
    Resources
    0.31
    èĥ½éĩı
    0.31
    è³ĩæºIJ
    0.31
    å¿ĥæĢĿ
    0.30
    Activations Density 0.961%

    No Known Activations