© 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. 23899
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĶŁæ´»æ°´å¹³
    -0.26
    çĸ£
    -0.25
    ÐĵÐŀ
    -0.25
     biçim
    -0.24
    (Label
    -0.23
     gated
    -0.23
    .HeaderText
    -0.23
     clientId
    -0.23
    rying
    -0.23
     Separate
    -0.23
    POSITIVE LOGITS
    æĹ¥èĩ³
    0.28
    semb
    0.28
    ayı
    0.26
    ).__
    0.26
    ább
    0.25
    expl
    0.25
    è¦ģä¹Ī
    0.25
    éļı
    0.25
    车ä¸Ĭ
    0.24
    ito
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.