© 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. 57289
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions

    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
    oure
    -0.27
    åľ¨çº¿åĴ¨è¯¢
    -0.26
    ä¸Ģå¼ł
    -0.25
    åĩłå¼ł
    -0.25
     quot
    -0.25
    visor
    -0.25
     buys
    -0.25
    .BL
    -0.25
    aily
    -0.25
    è°¯
    -0.24
    POSITIVE LOGITS
     appeared
    0.35
     originated
    0.35
     survived
    0.34
    åįłæį®äºĨ
    0.33
    缼è¡Į
    0.32
     likely
    0.32
     emerged
    0.31
    æµģè¡Į
    0.31
    èIJĮ
    0.31
    å´Ľèµ·
    0.30
    Activations Density 0.002%

    No Known Activations