© 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. 39708
    Prev
    Next
    INDEX
    Explanations

    N

    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
    umer
    -0.41
    g
    -0.39
    ão
    -0.38
    m
    -0.37
    úmero
    -0.37
    aming
    -0.36
    otes
    -0.36
    ote
    -0.36
    ature
    -0.35
    ews
    -0.35
    POSITIVE LOGITS
    el
    0.27
     enough
    0.25
    æĹłåı¯
    0.25
    æĹłæĥħ
    0.24
    es
    0.23
     ferv
    0.23
     similarly
    0.23
    Enough
    0.23
     suff
    0.23
     equally
    0.23
    Activations Density 70.253%

    No Known Activations