© 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. 24089
    Prev
    Next
    INDEX
    Explanations

    this/these

    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
    åŁºå»º
    -0.28
     feas
    -0.26
    aph
    -0.26
    ices
    -0.25
     pov
    -0.24
    .getPort
    -0.24
    ify
    -0.24
    ism
    -0.24
    uby
    -0.24
    yw
    -0.24
    POSITIVE LOGITS
    åĨĻäºĨ
    0.29
    ä¸ĭä¸Ģç¯ĩ
    0.28
    天é¹ħ
    0.27
    å¤į
    0.27
     reordered
    0.26
     дÑĢÑĥгие
    0.26
    peed
    0.26
     RequestOptions
    0.25
     styleUrls
    0.24
    éĥ½åľ¨
    0.24
    Activations Density 0.003%

    No Known Activations