© 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. 141427
    Prev
    Next
    INDEX
    Explanations

    woman -old

    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
    导èĪª
    -0.29
    æķĪåĬĽ
    -0.28
    ológico
    -0.27
    åIJ¯åĬ¨
    -0.26
    æīĵåĮħ
    -0.26
    -educated
    -0.26
    éĦĹ
    -0.25
     pedal
    -0.25
    æ½ĩ
    -0.24
    ç»ıèIJ¥ç®¡çIJĨ
    -0.24
    POSITIVE LOGITS
    ivement
    0.28
    åĩĨ
    0.27
    äºĴè¡¥
    0.27
    ÐłÐķ
    0.27
     Rush
    0.26
    GROUND
    0.25
     Tot
    0.25
    ASF
    0.25
    rush
    0.24
    noun
    0.24
    Activations Density 0.927%

    No Known Activations