© 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. 23649
    Prev
    Next
    INDEX
    Explanations

    copyright and distribution

    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
     Columbia
    -0.28
     optimized
    -0.26
    åĬ¨ä½ľ
    -0.25
    ervo
    -0.25
     contato
    -0.24
    èѬ
    -0.24
    åĬ²
    -0.24
    ille
    -0.24
    legg
    -0.24
    erty
    -0.24
    POSITIVE LOGITS
    åĪĩ
    0.29
    å¹³
    0.28
    -platform
    0.27
     subt
    0.26
     lim
    0.25
     platforms
    0.25
     Lim
    0.25
     complete
    0.25
    atism
    0.25
     candidates
    0.25
    Activations Density 0.005%

    No Known Activations