© 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. 56739
    Prev
    Next
    INDEX
    Explanations

    need

    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
    妨ç¢į
    -0.26
    mino
    -0.25
    ìļ´
    -0.25
    缺ä¹ı
    -0.25
    è¹Ĵ
    -0.24
    ä¸Ģç¬Ķ
    -0.24
     incapac
    -0.24
    issent
    -0.24
    ä¸įå®Į
    -0.24
    ä¸Ģè§Ĵ
    -0.24
    POSITIVE LOGITS
    è§Ħç¨ĭ
    0.33
    è®°ä½ı
    0.29
     remember
    0.29
     remembers
    0.29
    hei
    0.28
     redis
    0.26
     remembering
    0.26
    .gameserver
    0.26
     remembered
    0.25
    WebDriver
    0.25
    Activations Density 0.005%

    No Known Activations