© 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. 29587
    Prev
    Next
    INDEX
    Explanations

    about

    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
    ä¿Ŀ
    -0.30
    请
    -0.28
    ment
    -0.27
    åıij
    -0.27
    æ®Ĭ
    -0.26
     Soc
    -0.26
     kiÅŁi
    -0.26
    cente
    -0.26
    aur
    -0.25
    rir
    -0.25
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
    ä¹³èħº
    0.27
    Popular
    0.27
    è¿Ļ个éĹ®é¢ĺ
    0.26
    å¿Ĺ
    0.26
    æµģè¡ĮçļĦ
    0.26
    æ¶İ
    0.25
     floated
    0.25
    ugin
    0.25
    åħ¼åħ·
    0.24
    Activations Density 0.459%

    No Known Activations