© 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. 39681
    Prev
    Next
    INDEX
    Explanations

    Gran

    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
    -0.28
     candy
    -0.28
     rematch
    -0.27
     pink
    -0.26
     stalking
    -0.26
    课
    -0.26
     lesson
    -0.25
    łģ
    -0.25
     enrol
    -0.25
     tun
    -0.25
    POSITIVE LOGITS
     Sesso
    0.32
    apist
    0.29
    abet
    0.28
     Clin
    0.28
    alten
    0.27
     Cler
    0.26
    etur
    0.26
    ambi
    0.26
    <U
    0.26
    alt
    0.26
    Activations Density 2.267%

    No Known Activations