© 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. 25015
    Prev
    Next
    INDEX
    Explanations

    source code

    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
     rep
    -0.31
    ç»ıéªĮ
    -0.29
    æľī人
    -0.28
    åĩºå±Ģ
    -0.27
     experience
    -0.27
    æĹłäºº
    -0.27
    ScreenState
    -0.27
    amera
    -0.26
    [](
    -0.26
     cof
    -0.25
    POSITIVE LOGITS
    akit
    0.27
     honorable
    0.27
    ç¬ĥ
    0.26
    pat
    0.26
    inker
    0.25
    çļĦçĶŁåij½
    0.25
     denote
    0.25
    pa
    0.25
     unconditional
    0.25
    èĪĴéĢĤ
    0.24
    Activations Density 0.007%

    No Known Activations