© 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. 12-TRANSCODER-HP
    7. 23725
    Prev
    Next
    INDEX
    Explanations

    Code and compression concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĴ¥
    -0.32
    ouncer
    -0.28
    çĩİ
    -0.27
    çłĶ究æĬ¥åijĬ
    -0.27
    沸
    -0.27
    arium
    -0.27
    ç¿Ķ
    -0.27
    èľī
    -0.26
    èĢĥè¯ģ
    -0.25
    èħŃ
    -0.25
    POSITIVE LOGITS
    roman
    0.30
    满
    0.28
    anse
    0.26
     Gin
    0.26
     Responses
    0.26
    Responses
    0.26
    emens
    0.26
    specifier
    0.25
    /***/
    0.25
    responses
    0.25
    Activations Density 0.003%

    No Known Activations