© 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. 24195
    Prev
    Next
    INDEX
    Explanations

    positive or negative relationships

    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
    ahi
    -0.30
    ä½ķåĨµ
    -0.27
    scenario
    -0.27
     scenario
    -0.26
    åĽłä¸ºåľ¨
    -0.26
    ITTER
    -0.26
    åħ¨è¦ĨçĽĸ
    -0.25
    /lgpl
    -0.24
     Griff
    -0.24
    æľīä¸Ģç§į
    -0.24
    POSITIVE LOGITS
    Ãły
    0.28
    CCI
    0.26
    _nc
    0.26
    еб
    0.24
    _AC
    0.24
    IBUTES
    0.24
     AC
    0.24
     fences
    0.24
    æłĩæĿĨ
    0.23
    éģĹçķĻ
    0.23
    Activations Density 0.016%

    No Known Activations