© 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. 108025
    Prev
    Next
    INDEX
    Explanations

    technical/programming contexts

    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
    æĸĩåĮĸçļĦ
    -0.27
    mos
    -0.27
    èįı
    -0.25
    Aspect
    -0.25
    ist
    -0.25
     interpretation
    -0.25
    Äĥng
    -0.25
    åĮºæĶ¿åºľ
    -0.25
     <<
    -0.24
    atra
    -0.24
    POSITIVE LOGITS
    æľĢå¤ļçļĦ
    0.28
    ecurity
    0.26
     Mention
    0.26
    emax
    0.26
     fucks
    0.25
    ä½ĵéĩı
    0.25
    ework
    0.24
     payloads
    0.24
    çªĹæĪ·
    0.24
    rzy
    0.24
    Activations Density 0.057%

    No Known Activations