© 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. 19-TRANSCODER-HP
    7. 7684
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    еÑĢÑĭ
    -0.28
    çĭIJ
    -0.27
    æ£ĢæŁ¥
    -0.27
    erval
    -0.27
    edere
    -0.26
    ìĪľ
    -0.26
    getError
    -0.25
     checks
    -0.25
    çİĩ
    -0.24
    ede
    -0.24
    POSITIVE LOGITS
    raph
    0.32
    ç«ĭ
    0.29
    obby
    0.26
    åįķçĭ¬
    0.26
    ria
    0.25
    iasm
    0.24
    lement
    0.24
    ä¸įåħĭ
    0.24
     un
    0.24
    罨
    0.24
    Activations Density 0.004%

    No Known Activations