© 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. 39226
    Prev
    Next
    INDEX
    Explanations

    say "1"

    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
    5
    -0.30
    6
    -0.29
    4
    -0.28
    0
    -0.27
    3
    -0.26
    8
    -0.24
    7
    -0.24
    å±Ĭ
    -0.24
    caff
    -0.23
    9
    -0.22
    POSITIVE LOGITS
    1
    0.61
    ï¼ij
    0.59
    âĤģ
    0.56
    åįģä¸Ģ
    0.49
     eleven
    0.47
    ¹
    0.44
     nineteen
    0.42
     thirteen
    0.42
    ä¸ĢçĻ¾
    0.42
     twelve
    0.41
    Activations Density 89.476%

    No Known Activations