© 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. 35-TRANSCODER-HP
    7. 39759
    Prev
    Next
    INDEX
    Explanations

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Being
    -0.28
     èĭ
    -0.26
     being
    -0.26
    èĭ±çī¹
    -0.26
    Being
    -0.25
    .Inv
    -0.25
    个çĻ¾åĪĨ
    -0.25
    åºĶ该æĢİä¹Ī
    -0.25
    个交æĺĵ
    -0.25
    )[-
    -0.24
    POSITIVE LOGITS
    urally
    0.27
    notify
    0.27
    á»Ŀ
    0.25
    Ã¶ÃŁe
    0.25
    auer
    0.25
    outh
    0.25
     própria
    0.25
    lä
    0.24
    esso
    0.24
    nze
    0.24
    Activations Density 58.032%

    No Known Activations