© 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. 39090
    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
    ึà¸ģ
    -0.25
    ALSE
    -0.25
    бе
    -0.25
    unsafe
    -0.25
     NEGLIGENCE
    -0.24
    ocks
    -0.24
    hex
    -0.24
    atég
    -0.23
    ationally
    -0.23
    svn
    -0.23
    POSITIVE LOGITS
    ä»ĭ
    0.28
    æ¯ĶåĪĨ
    0.27
    ätt
    0.27
    mass
    0.26
     contracting
    0.26
    éĻµ
    0.26
    ç´¢
    0.25
    åѦåĪ°
    0.25
     lo
    0.25
    lo
    0.25
    Activations Density 1.104%

    No Known Activations

    This feature has no known activations.