© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    Slant, incline, or tilted

    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
    è¯įæĿ¡
    -0.30
    èĩªåĪ¶
    -0.30
    .vol
    -0.28
    herited
    -0.27
    ption
    -0.26
    åĬĽè¿ĺæĺ¯
    -0.26
    stands
    -0.25
    éĤ®ç®±
    -0.25
    vol
    -0.25
     volont
    -0.25
    POSITIVE LOGITS
     Establish
    0.31
    æ²®
    0.30
     Establishment
    0.28
     Established
    0.27
    ä»ŀ
    0.26
     establish
    0.25
    -establish
    0.24
    建ç«ĭ
    0.24
     Hole
    0.24
     established
    0.24
    Activations Density 0.007%

    No Known Activations