© 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. 39764
    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
    æ¯Ľ
    -0.27
    ä¹Ŀå·ŀ
    -0.27
     Fot
    -0.26
    Dec
    -0.26
    Develop
    -0.25
    Clo
    -0.25
    ting
    -0.25
    :
    -0.25
    Cele
    -0.25
    æµģ
    -0.24
    POSITIVE LOGITS
     minded
    0.28
     č↵ č↵
    0.28
     quits
    0.26
    æĢ§åij½
    0.26
     'č↵
    0.25
     spawned
    0.25
     regained
    0.25
    ifestyles
    0.25
     nonexistent
    0.24
     promised
    0.24
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.