© 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. 22419
    Prev
    Next
    INDEX
    Explanations

    Oil

    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
    plates
    -0.32
    illow
    -0.27
    ihar
    -0.26
    æīĢæıIJä¾ĽçļĦ
    -0.26
    åĨħ容ç®Ģä»ĭ
    -0.26
    缸è§ģ
    -0.26
    åĩłæŃ¥
    -0.26
    ParameterValue
    -0.25
    åıł
    -0.25
     HAR
    -0.24
    POSITIVE LOGITS
    Observable
    0.26
    .bs
    0.26
    isu
    0.26
    管
    0.25
     adjud
    0.25
     Anat
    0.24
    ERTICAL
    0.24
    ç´łè´¨
    0.24
     sworn
    0.24
    Vac
    0.24
    Activations Density 0.000%

    No Known Activations