© 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. 40160
    Prev
    Next
    INDEX
    Explanations

    hum

    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
     coordinate
    -0.27
     geçir
    -0.26
     doPost
    -0.25
     inve
    -0.25
     divisor
    -0.25
    å±Ĥå±Ĥ
    -0.24
    æµģåĬ¨
    -0.24
     bolt
    -0.24
     equipo
    -0.24
     dove
    -0.24
    POSITIVE LOGITS
    imations
    0.32
    çĪ±åIJĥ
    0.30
    prises
    0.29
    lers
    0.29
     uk
    0.29
    irma
    0.28
    imate
    0.28
    ики
    0.28
    ndon
    0.28
    inals
    0.28
    Activations Density 1.008%

    No Known Activations