© 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. 8876
    Prev
    Next
    INDEX
    Explanations

    official

    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
    åħ¸åŀĭ
    -0.29
    actual
    -0.27
    å®ŀéĻħ
    -0.27
    åħ·ä½ĵ
    -0.27
    naires
    -0.27
     actual
    -0.27
    è¡¥åħħ
    -0.26
    åİŁä»¶
    -0.25
    .ur
    -0.25
    å°ıé¢Ŀ
    -0.25
    POSITIVE LOGITS
     Union
    0.30
    azed
    0.28
     confusion
    0.25
    ä¹IJéĺŁ
    0.25
    人åijĺ
    0.24
     welcome
    0.24
     ÐłÐ¾ÑģÑģий
    0.24
    欢è¿İ
    0.24
     ÑģобÑĭÑĤи
    0.24
    tabl
    0.24
    Activations Density 0.008%

    No Known Activations