© 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. 18-TRANSCODER-HP
    7. 89584
    Prev
    Next
    INDEX
    Explanations

    since

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    изаÑĨии
    -0.27
    thresh
    -0.27
    ceil
    -0.26
    bara
    -0.25
    mode
    -0.25
    chl
    -0.25
    åľ¨é¦Ļ港
    -0.24
    istan
    -0.24
    iken
    -0.24
     HEADER
    -0.24
    POSITIVE LOGITS
     Affero
    0.28
     nak
    0.28
    æĬ¥éħ¬
    0.24
     Eisenhower
    0.24
     concede
    0.24
     Shank
    0.24
     ect
    0.24
    çIJĨç§ij
    0.23
    erea
    0.23
     dent
    0.23
    Activations Density 8.115%

    No Known Activations