© 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. 40222
    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
     understand
    -0.29
    çļĦåİĭåĬĽ
    -0.28
    綾
    -0.28
     seem
    -0.27
    ]=-
    -0.26
     an
    -0.25
    å½ĵ
    -0.25
     bring
    -0.25
    åİĭåĬĽ
    -0.25
     na
    -0.25
    POSITIVE LOGITS
     ogs
    0.30
    ologic
    0.30
    ellation
    0.29
    èŀįåIJĪåıijå±ķ
    0.29
    maries
    0.28
    Composite
    0.28
    Extras
    0.27
    istros
    0.27
    Above
    0.27
     undermin
    0.26
    Activations Density 2.812%

    No Known Activations

    This feature has no known activations.