© 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. 108519
    Prev
    Next
    INDEX
    Explanations

    some

    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
    umerator
    -0.27
     Furn
    -0.27
    ennes
    -0.27
    åľ°
    -0.26
     Lightweight
    -0.26
    åĿĩ
    -0.24
    ä¸ĢäºĽ
    -0.24
    æ³»
    -0.24
     Custom
    -0.24
    charset
    -0.24
    POSITIVE LOGITS
     activity
    0.29
     aspect
    0.28
     aspects
    0.27
    é«ĺçŃīéĻ¢æł¡
    0.27
     activities
    0.26
     kind
    0.26
    itra
    0.26
    fal
    0.26
     tang
    0.24
    aisy
    0.24
    Activations Density 0.546%

    No Known Activations