© 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. 95643
    Prev
    Next
    INDEX
    Explanations

    boolean

    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
    nr
    -0.31
    &S
    -0.30
    apus
    -0.26
     darn
    -0.25
    &(
    -0.25
    _platform
    -0.24
    platform
    -0.24
     platform
    -0.24
    té
    -0.24
    èħ¾
    -0.23
    POSITIVE LOGITS
    imap
    0.26
     bikini
    0.26
    пÑĢом
    0.26
     Verified
    0.25
    åĢ¾
    0.25
    uzzi
    0.24
     propos
    0.24
    logic
    0.24
     Gö
    0.24
    vier
    0.24
    Activations Density 0.107%

    No Known Activations