© 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. 151000
    Prev
    Next
    INDEX
    Explanations

    Possibly non-English / code snippets

    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
     ÑģледÑĥеÑĤ
    -0.24
    ile
    -0.24
    -shared
    -0.23
     Salv
    -0.23
     Teh
    -0.23
     initialValues
    -0.22
    ossip
    -0.22
     INS
    -0.22
     defaultProps
    -0.22
     sesso
    -0.22
    POSITIVE LOGITS
    æĶ¶çĽĬ
    0.27
    ERNEL
    0.26
    apl
    0.24
    产åĩº
    0.24
    ]</
    0.24
    累积
    0.24
     Showcase
    0.24
    ман
    0.24
    æīĵéĢļ
    0.23
    itchens
    0.23
    Activations Density 0.503%

    No Known Activations