© 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. 7769
    Prev
    Next
    INDEX
    Explanations

    specifications, components

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.25
    aveled
    -0.25
    pirit
    -0.25
    åĵªäºĽ
    -0.24
    seau
    -0.24
     Together
    -0.24
    è¿ĻäºĽä¸ľè¥¿
    -0.24
    ä¸ī代
    -0.24
    igid
    -0.24
    WebpackPlugin
    -0.23
    POSITIVE LOGITS
    cion
    0.27
    屡
    0.25
    åĩłä¹İæĺ¯
    0.25
     '".$
    0.24
    çĸĨ
    0.24
    ced
    0.24
    :disable
    0.24
    æ³Ħ
    0.24
    -Series
    0.23
    ony
    0.23
    Activations Density 0.013%

    No Known Activations