© 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. 9-TRANSCODER-HP
    7. 29604
    Prev
    Next
    INDEX
    Explanations

    sentence boundary/article segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¯Ħ
    -0.26
    stice
    -0.25
    ãĤ¸ãĥ£
    -0.25
    å¼ĺ
    -0.24
    amentals
    -0.23
    esters
    -0.23
    orida
    -0.23
    Wunused
    -0.23
    ala
    -0.23
    (&(
    -0.23
    POSITIVE LOGITS
    GT
    0.26
    æľ¬é¢Ĩ
    0.26
    GC
    0.25
    rated
    0.25
    Compat
    0.25
    æ¯Ľå·¾
    0.24
    latent
    0.24
     conven
    0.24
     wen
    0.24
    means
    0.24
    Activations Density 4.152%

    No Known Activations