© 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. 23-TRANSCODER-HP
    7. 24656
    Prev
    Next
    INDEX
    Explanations

    article/blog post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     us
    -0.31
    åĵº
    -0.30
    ime
    -0.28
    2
    -0.27
     asc
    -0.27
    1
    -0.26
    w
    -0.26
    æĺĤ
    -0.25
    8
    -0.25
    wh
    -0.25
    POSITIVE LOGITS
     misunderstanding
    0.67
    误解
    0.66
     misconception
    0.66
     misunderstood
    0.64
    å¾Īå¤ļ人
    0.62
     miscon
    0.61
     misunderstand
    0.59
     mistakenly
    0.58
    误åĮº
    0.57
     mistaken
    0.57
    Activations Density 0.004%

    No Known Activations