© 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. 23359
    Prev
    Next
    INDEX
    Explanations

    neuro

    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
    loh
    -0.29
    elay
    -0.26
    ãĥıãĥ³
    -0.25
    IDL
    -0.24
    ëĶľ
    -0.24
    /fr
    -0.24
    abolic
    -0.24
     Jah
    -0.24
    Curve
    -0.24
    为空
    -0.23
    POSITIVE LOGITS
    åĪĽéĢłæĢ§
    0.26
    á»ĵn
    0.26
    illus
    0.26
    shelf
    0.25
    _der
    0.25
     integrates
    0.25
    mir
    0.25
    eways
    0.24
    群
    0.24
    è¿ĺ羣
    0.24
    Activations Density 0.011%

    No Known Activations