© 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. 109156
    Prev
    Next
    INDEX
    Explanations

    code and technical documents

    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
    å®ĮæĪIJ
    -0.37
     done
    -0.35
     behind
    -0.35
     out
    -0.34
     dust
    -0.33
    åĩºæĿ¥
    -0.33
    å®ĮæĪIJåIJİ
    -0.33
     completed
    -0.32
    å®Įæ¯ķ
    -0.32
     finished
    -0.31
    POSITIVE LOGITS
    aley
    0.27
     nic
    0.27
    ÑĢож
    0.26
    NIC
    0.25
    //:
    0.25
    bef
    0.25
    Ñģол
    0.25
    aders
    0.24
     ([[
    0.24
    izin
    0.24
    Activations Density 0.919%

    No Known Activations