© 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. 8580
    Prev
    Next
    INDEX
    Explanations

    2

    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
     germ
    -0.27
    éĹª
    -0.25
    agger
    -0.25
     starting
    -0.25
    inton
    -0.25
     Orr
    -0.24
    å§ĭ
    -0.24
    GIN
    -0.24
    ä¸įå¿į
    -0.24
    BG
    -0.23
    POSITIVE LOGITS
    ves
    0.30
    çł´éŨ
    0.26
     ejected
    0.26
     touches
    0.24
    æĮĤéĴ©
    0.24
    ä¸Ĭ线
    0.24
     times
    0.24
    åĿIJä¸ĭ
    0.24
    cion
    0.24
    æĹłçº¿
    0.24
    Activations Density 0.114%

    No Known Activations