© 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. 29980
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    bud
    -0.30
    æݧåĪ¶åĻ¨
    -0.28
    大éĺŁ
    -0.27
    kur
    -0.26
    park
    -0.25
    DataExchange
    -0.25
     Oval
    -0.24
    è¿IJåĬ¨
    -0.24
    çģ«èĬ±
    -0.24
    éĺŁ
    -0.24
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.27
    个å¤ļ
    0.27
    éĢ¢
    0.27
     Emanuel
    0.26
    _bridge
    0.26
    æĢľ
    0.26
    roids
    0.25
    -platform
    0.25
     onSave
    0.25
    æŃ»åIJİ
    0.24
    Activations Density 0.486%

    No Known Activations