© 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. 30-TRANSCODER-HP
    7. 95782
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī¯
    -0.27
    -resistant
    -0.27
    SWG
    -0.26
    äºĮ代
    -0.25
     close
    -0.25
    @Enable
    -0.25
     res
    -0.25
    blade
    -0.25
    Assertions
    -0.24
    缮ãģ®
    -0.24
    POSITIVE LOGITS
    äºı
    0.27
    peak
    0.26
    ALLE
    0.25
    éĺ¶
    0.25
    łģ
    0.25
     Ott
    0.24
    -null
    0.24
    ä¸¤åľ°
    0.24
    ilst
    0.24
    äºĨåĩł
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.