© 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. 150539
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
     loop
    -0.29
     foot
    -0.27
    ape
    -0.26
    佯
    -0.26
     loops
    -0.25
    mite
    -0.24
     looping
    -0.24
    arse
    -0.23
    (loop
    -0.23
    illation
    -0.23
    POSITIVE LOGITS
    dana
    0.29
    æŃ£è§Ħ
    0.28
    icana
    0.28
     Fathers
    0.26
    æĪIJåIJį
    0.24
    Speaking
    0.24
    ()(
    0.24
    è³´
    0.24
    iets
    0.24
    é¼ĵ
    0.24
    Activations Density 0.120%

    No Known Activations