© 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. 9-TRANSCODER-HP
    7. 29747
    Prev
    Next
    INDEX
    Explanations

    reach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı£æ°Ķ
    -0.31
    AndGet
    -0.27
    _snapshot
    -0.25
    _overflow
    -0.25
    å¸ĮæľĽ
    -0.25
    å°ij
    -0.25
    æ¹¾
    -0.25
     unpack
    -0.24
    ationally
    -0.24
    éĬ®
    -0.24
    POSITIVE LOGITS
     Zodiac
    0.30
    íĴĪ
    0.28
    Composer
    0.28
     Composer
    0.27
    alem
    0.26
    åĮĹæŀģ
    0.25
    aget
    0.25
    ullo
    0.24
     Classes
    0.24
    åĽ¢éķ¿
    0.24
    Activations Density 0.668%

    No Known Activations