© 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. 24808
    Prev
    Next
    INDEX
    Explanations

    :

    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
    严åİīæīĵåĩ»
    -0.30
    åįĩ级
    -0.29
    ä¸ī个
    -0.27
    åij½è¿IJ
    -0.27
    ä¸Ģ个
    -0.27
     purs
    -0.27
    åıĮéĩį
    -0.26
    åħŃ个
    -0.25
    羿
    -0.25
    éķ¿å¾Ĺ
    -0.24
    POSITIVE LOGITS
    enario
    0.30
    ocus
    0.27
    ilage
    0.26
    ffb
    0.25
    ifty
    0.25
    ç²²
    0.25
    swer
    0.25
    enan
    0.25
    gart
    0.24
     consensus
    0.24
    Activations Density 0.002%

    No Known Activations