© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9540
    Prev
    Next
    INDEX
    Explanations

    increasing

    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
    æĹłæķ°æ¬¡
    -0.33
    鸳
    -0.32
    tee
    -0.28
    -support
    -0.27
    åĩłæ¬¡
    -0.27
    ä¸į足以
    -0.27
    æ³ķåĪ¶
    -0.27
    å¤ļ次
    -0.27
    -rad
    -0.26
    è´¨æĦŁ
    -0.26
    POSITIVE LOGITS
     concern
    0.28
     concerns
    0.27
    ort
    0.27
     charts
    0.26
    æŃ»äº¡
    0.26
    -org
    0.25
     diagnosis
    0.25
     alarmed
    0.25
     among
    0.25
    ORT
    0.25
    Activations Density 0.014%

    No Known Activations