© 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. 40148
    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
    umas
    -0.27
     reflective
    -0.27
    ">//
    -0.26
    ATAR
    -0.25
    sizeof
    -0.25
    stile
    -0.25
    ä½ĵ系建设
    -0.25
    yen
    -0.24
    theid
    -0.24
    å®Įæķ´çļĦ
    -0.24
    POSITIVE LOGITS
     distance
    0.27
     draw
    0.27
    OW
    0.26
     distancia
    0.25
    away
    0.25
     pity
    0.25
     hang
    0.25
    distance
    0.25
     draws
    0.25
    æ°ij
    0.25
    Activations Density 0.568%

    No Known Activations

    This feature has no known activations.