© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 339
    Prev
    Next
    INDEX
    Explanations

    ] )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palace
    -0.25
    ì°¬
    -0.25
    /front
    -0.25
    lus
    -0.25
    ordinated
    -0.24
    ä¸Ģè´¯
    -0.24
    å¾Ģå¹´
    -0.24
     oven
    -0.23
     Hastings
    -0.23
     vor
    -0.23
    POSITIVE LOGITS
    åıŁ
    0.26
    encil
    0.25
    ABB
    0.24
     Senators
    0.24
    uary
    0.24
    ä¸Ģç§Ĵ
    0.24
    被æ·ĺæ±°
    0.24
    WAR
    0.24
    æııåĨĻ
    0.23
     Peek
    0.23
    Activations Density 8.065%

    No Known Activations