© 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. 108345
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    kits
    -0.30
     region
    -0.27
    айд
    -0.26
    large
    -0.26
     Large
    -0.25
    æ³ł
    -0.25
    大èĩ£
    -0.25
    adesh
    -0.24
    伸åĩº
    -0.24
    ices
    -0.24
    POSITIVE LOGITS
     sense
    0.30
     Sense
    0.28
    \Queue
    0.26
    LEM
    0.26
    椰
    0.25
    pto
    0.25
    çľ¼ä¸Ń
    0.25
    uristic
    0.24
    æįķ
    0.24
    sense
    0.23
    Activations Density 0.146%

    No Known Activations