© 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. 24109
    Prev
    Next
    INDEX
    Explanations

    advance

    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
    衽
    -0.27
     Kont
    -0.26
    ////////////
    -0.25
    quine
    -0.24
     regulator
    -0.23
    inus
    -0.23
    å«Ĥ
    -0.23
     dojo
    -0.23
     Oman
    -0.23
    lane
    -0.23
    POSITIVE LOGITS
    åıijå±ķä¸Ń
    0.34
     progress
    0.33
     development
    0.29
    åıijå±ķ
    0.29
     efforts
    0.29
     construction
    0.28
     progression
    0.28
    èĢħçļĦ
    0.27
     attempts
    0.27
    çļĦåıijå±ķ
    0.27
    Activations Density 0.026%

    No Known Activations