© 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. 39951
    Prev
    Next
    INDEX
    Explanations

    The state

    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
     phẩm
    -0.26
     archae
    -0.26
     hopeful
    -0.26
     supportive
    -0.25
    utable
    -0.24
     artificial
    -0.24
     dest
    -0.24
     firstly
    -0.24
    atisf
    -0.24
     departed
    -0.23
    POSITIVE LOGITS
    sets
    0.34
    scar
    0.32
    sts
    0.31
    thin
    0.31
    systems
    0.30
    stration
    0.30
    sson
    0.30
    strict
    0.30
    stor
    0.30
    sons
    0.29
    Activations Density 1.005%

    No Known Activations