© 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. 23-TRANSCODER-HP
    7. 24897
    Prev
    Next
    INDEX
    Explanations

    fire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noinspection
    -0.28
    icism
    -0.26
    æŀĦ
    -0.26
     HALF
    -0.25
    createClass
    -0.25
    Subsystem
    -0.25
    opard
    -0.25
    èIJ¥
    -0.24
    åĭº
    -0.24
    代价
    -0.24
    POSITIVE LOGITS
    que
    0.31
    註
    0.30
    ified
    0.28
    ized
    0.27
    OC
    0.27
    ly
    0.26
     ann
    0.26
    ç»Ļèĩªå·±
    0.26
    ated
    0.25
    ged
    0.25
    Activations Density 0.008%

    No Known Activations