© 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. 20-TRANSCODER-HP
    7. 63401
    Prev
    Next
    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éħĴä¸ļ
    -0.26
    depend
    -0.25
    ]%
    -0.25
    éĺ±
    -0.25
    客æĪ·éľĢæ±Ĥ
    -0.25
    å±ħæ°ij
    -0.24
    Conditions
    -0.24
     Deal
    -0.24
    ç§ģæľį
    -0.23
     Claw
    -0.23
    POSITIVE LOGITS
    /files
    0.32
     alphabet
    0.30
     cast
    0.27
     hears
    0.27
    åIJ¬
    0.27
    nut
    0.26
     heard
    0.25
    alphabet
    0.25
    onor
    0.25
     Tonight
    0.24
    Activations Density 1.480%

    No Known Activations