© 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. 39512
    Prev
    Next
    INDEX
    Explanations

    say char

    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
     Certain
    -0.28
     Classical
    -0.27
    åºļ
    -0.27
     Certainly
    -0.26
     certain
    -0.26
    ä¹Łä¸įä¼ļ
    -0.26
     Object
    -0.25
    缮ãģ®
    -0.25
    Certainly
    -0.25
     Gerald
    -0.25
    POSITIVE LOGITS
    auce
    0.31
    azar
    0.30
    azor
    0.30
    rax
    0.29
    hand
    0.29
    rox
    0.29
    aval
    0.29
    caf
    0.29
    char
    0.28
    ricao
    0.28
    Activations Density 0.235%

    No Known Activations