© 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. 30-TRANSCODER-HP
    7. 95928
    Prev
    Next
    INDEX
    Explanations

    Animals, places, and structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apot
    -0.27
    tp
    -0.26
    ÑĤиÑĢов
    -0.26
    ows
    -0.25
    protocol
    -0.25
    поÑĩ
    -0.25
    ÑıÑĤÑģÑı
    -0.25
    OTES
    -0.24
    ntax
    -0.24
    protocols
    -0.24
    POSITIVE LOGITS
     Mafia
    0.29
    alse
    0.27
    èĩªè±ª
    0.27
    odel
    0.26
    bars
    0.26
    åĻ¨
    0.26
    ularity
    0.25
    FileStream
    0.25
    ç¢į
    0.25
    åı£æ°´
    0.25
    Activations Density 0.101%

    No Known Activations