© 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. 7886
    Prev
    Next
    INDEX
    Explanations

    Normal text

    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
    igaret
    -0.27
    >>>(
    -0.25
    heels
    -0.23
    追赶
    -0.23
    渤海
    -0.23
    babel
    -0.23
    >>(
    -0.22
    -shot
    -0.22
     Body
    -0.22
    /bar
    -0.22
    POSITIVE LOGITS
    罩
    0.25
    votes
    0.24
    èĤª
    0.24
    ä¸ĢåĪ»
    0.24
     insign
    0.24
    åĿ©
    0.24
    çģ¾
    0.23
    è¯Ģ
    0.23
     fiss
    0.23
    chw
    0.23
    Activations Density 0.002%

    No Known Activations