© 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. 27-TRANSCODER-HP
    7. 8758
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ī
    -0.27
    æ½ľèĥ½
    -0.26
    çĽĹ
    -0.26
    aya
    -0.25
    éĩįå¿ĥ
    -0.25
    å¹£
    -0.25
    ä¸Ģè§Ĵ
    -0.25
    éĽķåĥı
    -0.24
    纪念ç¢ij
    -0.24
    çݩ家æĿ¥è¯´
    -0.24
    POSITIVE LOGITS
     vice
    0.27
     ÑĢеакÑĨи
    0.26
    vk
    0.25
     optim
    0.25
    olina
    0.25
    .Resolve
    0.24
     serial
    0.24
     Faul
    0.24
    Raw
    0.24
    íĬ¸
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.