© 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. 30-TRANSCODER-HP
    7. 96021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æłĩ
    -0.29
    eci
    -0.27
    åIJĽ
    -0.27
    ạc
    -0.27
     global
    -0.26
    culo
    -0.26
    åį¿
    -0.25
    _simps
    -0.24
    loc
    -0.23
    unt
    -0.23
    POSITIVE LOGITS
    ç¼°
    0.29
    å¸Ĥéķ¿
    0.27
     ALIGN
    0.26
    orea
    0.25
     getDate
    0.25
    arily
    0.24
    TRACE
    0.24
    ç±
    0.24
    çĶ¨æĪ·æıIJä¾Ľ
    0.24
    延éķ¿
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.