© 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. 56662
    Prev
    Next
    INDEX
    Explanations

    social/political topics

    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
    åĩºåľº
    -0.30
    æķŀå¼Ģ
    -0.27
    èĭ«
    -0.26
    è¿ĶåĽŀæIJľçĭIJ
    -0.26
    åIJĥ
    -0.26
    isz
    -0.26
    åIJĥå®Į
    -0.25
    éĢłèĪ¹
    -0.25
    uations
    -0.25
    èĪ¹ä¸Ĭ
    -0.25
    POSITIVE LOGITS
     managed
    0.28
    禽
    0.27
     NGOs
    0.26
    åŁ¹è®Ń
    0.26
    èĢĨ
    0.26
     tutor
    0.25
     workspace
    0.25
     trained
    0.25
     Tutor
    0.25
    åĬ²
    0.25
    Activations Density 0.001%

    No Known Activations