© 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. 39996
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     needs
    -0.28
    ban
    -0.27
    ’
    -0.26
     bu
    -0.25
    çĶµæ±ł
    -0.25
     line
    -0.24
     B
    -0.24
    rest
    -0.24
    u
    -0.23
    er
    -0.23
    POSITIVE LOGITS
     зÑĢ
    0.25
    maal
    0.24
     zob
    0.24
     accol
    0.24
     getResult
    0.23
    æĮ¯ãĤĬ
    0.23
     adore
    0.23
    xlim
    0.23
    -tm
    0.23
     misd
    0.23
    Activations Density 6.532%

    No Known Activations

    This feature has no known activations.