© 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. 14-TRANSCODER-HP
    7. 40233
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.29
     Fall
    -0.25
    åĢĴ
    -0.25
    ole
    -0.24
    estion
    -0.24
    +E
    -0.24
    don
    -0.23
     ÐľÐµ
    -0.23
    reme
    -0.23
     hose
    -0.23
    POSITIVE LOGITS
    å°±è¿ŀ
    0.28
    è¯ģ
    0.28
    ijkl
    0.26
     Bulls
    0.26
    itches
    0.26
    parity
    0.26
    visa
    0.26
    ivos
    0.25
     Stadium
    0.25
     Tits
    0.25
    Activations Density 1.146%

    No Known Activations

    This feature has no known activations.