© 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. 27-TRANSCODER-HP
    7. 8877
    Prev
    Next
    INDEX
    Explanations

    Code, questions, menus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osl
    -0.27
    mint
    -0.27
    atching
    -0.27
    chal
    -0.26
    iri
    -0.26
    rede
    -0.25
    itian
    -0.25
     Maiden
    -0.25
     lad
    -0.25
     меÑĤÑĢо
    -0.25
    POSITIVE LOGITS
    _jump
    0.28
    èħ¹
    0.27
     mens
    0.27
     jumped
    0.26
    adoras
    0.26
    onica
    0.25
    èĥ´
    0.25
    æľĢéĩįè¦ģ
    0.24
    <message
    0.24
     abdominal
    0.24
    Activations Density 0.000%

    No Known Activations