© 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. 108022
    Prev
    Next
    INDEX
    Explanations

    technical informational writing

    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
     Ded
    -0.28
    MOTE
    -0.26
    çľĭçĤ¹
    -0.26
     lạc
    -0.26
    æĸ°ä¸ļæĢģ
    -0.25
    uida
    -0.25
    æľ¨èĢ³
    -0.25
     hero
    -0.24
     PTR
    -0.24
    æ¡«
    -0.24
    POSITIVE LOGITS
    edral
    0.30
    nis
    0.28
    éī´
    0.26
    èµĮ
    0.26
    åħħåĪĨ
    0.26
    请æ±Ĥ
    0.25
     ankles
    0.25
    ed
    0.25
     valign
    0.25
    æĶ¯éħį
    0.24
    Activations Density 0.900%

    No Known Activations