© 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. 9324
    Prev
    Next
    INDEX
    Explanations

    prone

    np_max-act-logits · gemini-2.0-flash
    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
     Tos
    -0.29
    ialized
    -0.29
    说æĺ¯
    -0.26
    eding
    -0.26
    NJ
    -0.26
    thon
    -0.25
    urally
    -0.25
    çıł
    -0.25
    eled
    -0.24
    _ios
    -0.24
    POSITIVE LOGITS
     needed
    0.25
    å¦Ĭ
    0.23
     suffered
    0.23
    eeee
    0.23
     developmental
    0.23
     eligible
    0.23
    å¿ĥè¡Ģ
    0.22
     Ngoại
    0.22
    .fc
    0.22
    velopment
    0.22
    Activations Density 0.851%

    No Known Activations