© 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. 40256
    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
    	NULL
    -0.27
    cie
    -0.27
    egin
    -0.26
     vá»įng
    -0.26
    console
    -0.25
    ,SIGNAL
    -0.25
    HEET
    -0.25
    عد
    -0.25
    ailing
    -0.24
    ail
    -0.24
    POSITIVE LOGITS
    (rad
    0.26
    iere
    0.26
    izon
    0.24
    pray
    0.23
    çĶļèĩ³è¿ŀ
    0.23
    çĶļèĩ³
    0.23
    ysz
    0.23
    Place
    0.23
     dela
    0.23
     place
    0.23
    Activations Density 1.259%

    No Known Activations

    This feature has no known activations.