© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6999
    Prev
    Next
    INDEX
    Explanations

    goals and targets

    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
    liable
    -0.26
     Bucc
    -0.26
    åı¯èĥ½åıijçĶŁ
    -0.26
    й
    -0.25
    LIKELY
    -0.25
    è°Į
    -0.24
    缴æݥ影åĵį
    -0.24
    æºIJæºIJä¸įæĸŃ
    -0.24
    æ§Ł
    -0.23
    ignum
    -0.23
    POSITIVE LOGITS
    /topics
    0.29
     or
    0.28
     but
    0.27
     and
    0.26
     slightly
    0.26
     vi
    0.25
     in
    0.25
     und
    0.25
     Single
    0.24
    phas
    0.24
    Activations Density 0.021%

    No Known Activations