© 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. 32-TRANSCODER-HP
    7. 41629
    Prev
    Next
    INDEX
    Explanations

    healthy/normal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /stdc
    -0.26
    frag
    -0.25
    oft
    -0.25
    .words
    -0.25
    訴
    -0.24
    PM
    -0.24
    æ¦ľ
    -0.24
    _ARR
    -0.24
    ãĥ¡ãĥ³ãĥĪ
    -0.24
    naments
    -0.23
    POSITIVE LOGITS
     hearts
    0.37
     levels
    0.34
    çļĦå¿ĥ
    0.31
    åĬŁ
    0.30
    -heart
    0.28
    levels
    0.27
    lvl
    0.27
    çļĦçľ¼çĿĽ
    0.26
     Levels
    0.26
    -mon
    0.26
    Activations Density 0.001%

    No Known Activations