© 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. 109078
    Prev
    Next
    INDEX
    Explanations

    source/sources

    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
    æµĭ
    -0.32
    itore
    -0.26
    zes
    -0.26
    仪
    -0.26
    åıĤ
    -0.25
     partager
    -0.25
    åĽłåľ°
    -0.25
     Prediction
    -0.25
    éĿ¶
    -0.25
    Prediction
    -0.25
    POSITIVE LOGITS
    è¹Ĭ
    0.29
    gal
    0.29
     histor
    0.26
    åĴ©
    0.26
    -conscious
    0.25
     concerning
    0.25
    paragraph
    0.25
     dealing
    0.25
    oque
    0.25
    lish
    0.25
    Activations Density 0.903%

    No Known Activations