© 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. 25-TRANSCODER-HP
    7. 107873
    Prev
    Next
    INDEX
    Explanations

    Career-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īåľ°æĸ¹
    -0.31
    æľ¬ç½ijç«Ļ
    -0.26
    åĩłå®¶
    -0.26
    åıĮèħ¿
    -0.26
    abd
    -0.26
    çªĸ
    -0.26
     finalists
    -0.25
    Site
    -0.24
     surrender
    -0.24
     undercut
    -0.24
    POSITIVE LOGITS
    äºĪ
    0.28
    幺
    0.28
    __((
    0.27
    orean
    0.27
    omatic
    0.27
    onis
    0.26
    care
    0.26
    postgres
    0.26
    é¾Ħ
    0.26
    ski
    0.26
    Activations Density 0.916%

    No Known Activations