© 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. 27-TRANSCODER-HP
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    Notifications or receiving something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     motivate
    -0.30
    leans
    -0.29
     Generate
    -0.26
    Ĩµ
    -0.26
     LY
    -0.25
    -java
    -0.25
     NYT
    -0.25
    анÑģ
    -0.25
    ä¸Ģçŀ¬éĹ´
    -0.24
     Tyson
    -0.24
    POSITIVE LOGITS
    riminal
    0.31
    imately
    0.29
    ected
    0.28
    resse
    0.28
    éĤ£ä¹Īç®Ģåįķ
    0.26
    表æ¼Ķ
    0.26
    æ¼Ķåĩº
    0.26
    å®ļåIJij
    0.26
    blade
    0.26
    çĤ¹å¤ļ
    0.26
    Activations Density 0.918%

    No Known Activations