© 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. 14-TRANSCODER-HP
    7. 40564
    Prev
    Next
    INDEX
    Explanations

    self-interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªå·±
    -0.27
    åħ¬çĶ¨
    -0.26
     Independent
    -0.26
    fy
    -0.26
    å¦Ĥæľī
    -0.25
    èĩªå®¶
    -0.25
    Independent
    -0.25
    _dyn
    -0.25
    ANE
    -0.24
    ive
    -0.24
    POSITIVE LOGITS
    lew
    0.28
    è´£
    0.28
    ¢åįķ
    0.27
    éªĨ
    0.26
    elist
    0.25
    .jp
    0.25
    .Win
    0.25
     kup
    0.25
    責
    0.24
     Woj
    0.24
    Activations Density 0.615%

    No Known Activations