© 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. 19-TRANSCODER-HP
    7. 8792
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è½®
    -0.28
    å¶Ĥ
    -0.26
    probe
    -0.26
     probe
    -0.25
     полÑĮз
    -0.25
     Probe
    -0.25
    acam
    -0.25
    alley
    -0.25
    çĶµä¿¡
    -0.24
    _probe
    -0.24
    POSITIVE LOGITS
    说åĪ°
    0.32
    urat
    0.27
    chio
    0.27
    çļĦæ¯į亲
    0.27
    ti
    0.27
     said
    0.27
    åįĹå±±
    0.26
     superior
    0.26
    si
    0.25
    ket
    0.25
    Activations Density 1.069%

    No Known Activations

    This feature has no known activations.