© 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. 29656
    Prev
    Next
    INDEX
    Explanations

    alternatively/additionally

    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
    计åħ¥
    -0.25
    avier
    -0.25
    Io
    -0.24
     jou
    -0.24
    .tf
    -0.23
    TEL
    -0.23
     shepherd
    -0.23
     Io
    -0.23
    é¾Ł
    -0.22
    çī¢è®°ä½¿åij½
    -0.22
    POSITIVE LOGITS
    å¤ľéĩĮ
    0.28
    读èĢħ
    0.26
    æ¸ħåĩī
    0.26
    Ỽ
    0.25
    åIJĥ
    0.24
    åĴĶ
    0.24
    ãĥīãĥ©
    0.24
     Bronx
    0.23
     tens
    0.23
    æŀ¶
    0.23
    Activations Density 0.771%

    No Known Activations