© 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. 39845
    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
    variants
    -0.32
    梦è§ģ
    -0.29
    variant
    -0.28
    imson
    -0.26
    ermen
    -0.26
    太ä¹ħ
    -0.26
    inner
    -0.25
    tails
    -0.25
    ç»ıéªĮåĴĮ
    -0.24
    ieri
    -0.24
    POSITIVE LOGITS
    ICENSE
    0.27
    -hole
    0.27
    ixe
    0.27
    utory
    0.26
    è¤Ĥ
    0.25
    пиÑģÑĮ
    0.25
    å¬ĸ
    0.25
    æ½Ĩ
    0.24
     changes
    0.24
    çī¹åĪ«å£°æĺİ
    0.24
    Activations Density 2.490%

    No Known Activations

    This feature has no known activations.