© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    Discussions and information

    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
    dle
    -0.28
    Solid
    -0.25
    vides
    -0.24
    è¨Ĺ
    -0.24
    ä¿ĿçķĻ
    -0.24
    shore
    -0.24
    tons
    -0.24
     solid
    -0.24
    mq
    -0.23
    æŃ¥
    -0.23
    POSITIVE LOGITS
     ranging
    0.32
    kish
    0.27
     dating
    0.26
    omic
    0.26
    quee
    0.26
    pecific
    0.26
    etting
    0.26
     rek
    0.25
    /problems
    0.25
    ekt
    0.25
    Activations Density 0.876%

    No Known Activations