© 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. 32-TRANSCODER-HP
    7. 42066
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ½è¢«
    -0.25
    亲åŃIJ
    -0.24
     Nunes
    -0.24
    å¯ĵ
    -0.24
    æİĪ
    -0.24
    éĥ½æ²¡æľī
    -0.24
    æ²Ļ
    -0.24
    èĤ¡
    -0.23
     socially
    -0.23
    åĨħåľ°
    -0.23
    POSITIVE LOGITS
     specification
    0.34
     specifications
    0.30
    exact
    0.27
    specs
    0.27
     Cv
    0.27
     specs
    0.26
    å®ŀè·µç»ıéªĮ
    0.26
    -select
    0.26
     feast
    0.26
    Specifications
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.