© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    journal articles and citations

    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
     scratch
    -0.29
    å¹¾ä¹İ
    -0.27
    lut
    -0.26
     اÙĦشر
    -0.25
    vice
    -0.25
    _('
    -0.25
    åĩłä¹İæīĢæľī
    -0.25
    'L
    -0.24
    VES
    -0.24
    really
    -0.24
    POSITIVE LOGITS
    éĢĬ
    0.26
    ono
    0.26
    onom
    0.25
    POCH
    0.25
    oad
    0.24
    æ¯Ĵ
    0.24
    otonin
    0.24
    Bars
    0.23
    еÑĢÑĭ
    0.23
    åħ¥
    0.23
    Activations Density 0.116%

    No Known Activations