© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    face

    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
    è¾ĺ
    -0.29
     orth
    -0.27
    å½ĵä¸Ń
    -0.25
    gesch
    -0.24
    ä¸Ģ身
    -0.24
     mitt
    -0.24
     procur
    -0.24
     reun
    -0.24
     Bands
    -0.24
    eva
    -0.23
    POSITIVE LOGITS
    orial
    0.33
    æĸ½
    0.26
    ÑĮÑı
    0.26
    '*
    0.25
     instruction
    0.25
     acknowledge
    0.24
    #line
    0.24
     acknow
    0.24
     forcefully
    0.24
    åĽŀå¿Ĩ
    0.23
    Activations Density 0.103%

    No Known Activations