© 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. 108096
    Prev
    Next
    INDEX
    Explanations

    APIs and servers

    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
    Kel
    -0.31
    pest
    -0.29
    orient
    -0.26
    YLE
    -0.26
    éĩį伤
    -0.26
     kel
    -0.25
     Kel
    -0.24
     ben
    -0.24
    åıĺ
    -0.24
     Kenn
    -0.24
    POSITIVE LOGITS
     APIs
    0.42
     API
    0.39
     middleware
    0.39
     interoper
    0.37
     server
    0.32
     implementation
    0.31
     servers
    0.30
    API
    0.30
     implementations
    0.30
    .API
    0.29
    Activations Density 1.275%

    No Known Activations