© 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. 23-TRANSCODER-HP
    7. 23989
    Prev
    Next
    INDEX
    Explanations

    Signing up or attending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    常年
    -0.34
    mentor
    -0.30
    éķ¿æľŁ
    -0.28
    æĦıå¿Ĺ
    -0.26
    -season
    -0.25
    çĥ¦
    -0.25
     invitation
    -0.25
    ÑĢоÑģ
    -0.24
    pan
    -0.24
    ion
    -0.24
    POSITIVE LOGITS
    icum
    0.28
    å®ŀéªĮ
    0.26
     experiment
    0.26
    ä½ĵéªĮ
    0.26
    å°ıå¿ĥ
    0.25
     others
    0.25
    ÑĥÑĩа
    0.25
    ICA
    0.25
     experimented
    0.25
    æĥŁ
    0.24
    Activations Density 0.004%

    No Known Activations