© 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. 40038
    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
    -ID
    -0.29
    oo
    -0.28
    ä¸ĬéĻIJ
    -0.28
     preced
    -0.26
    Ñij
    -0.26
    ãĤĴå¾Ĺ
    -0.26
    oning
    -0.25
    ãn
    -0.25
    aisy
    -0.25
    )\
    -0.24
    POSITIVE LOGITS
    tested
    0.28
     elevated
    0.28
    indle
    0.27
    æ·¡æ·¡çļĦ
    0.26
     virtues
    0.26
    nection
    0.25
    tered
    0.25
     great
    0.25
    ialized
    0.25
     regarded
    0.25
    Activations Density 0.521%

    No Known Activations

    This feature has no known activations.