© 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. 25-TRANSCODER-HP
    7. 107927
    Prev
    Next
    INDEX
    Explanations

    Short random strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaction
    -0.35
     Reaction
    -0.32
     kinetics
    -0.31
    .react
    -0.31
    reaction
    -0.30
    åıijéħµ
    -0.30
     reacting
    -0.29
     reactions
    -0.29
    Ign
    -0.28
     reacted
    -0.28
    POSITIVE LOGITS
    ADR
    0.30
    Dis
    0.30
    å¡«
    0.29
    -dropdown
    0.29
    æ¤į
    0.28
    ç²īç¢İ
    0.27
     Dis
    0.27
    èĻļ
    0.27
    udo
    0.26
     discontin
    0.26
    Activations Density 1.196%

    No Known Activations