© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    horror and fear

    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
    erver
    -0.31
    ainer
    -0.30
    ÙĦÙĩ
    -0.29
    bies
    -0.28
    ãĥ³ãĤ°
    -0.28
    ÑĥÑĩа
    -0.27
     ENT
    -0.26
    ervers
    -0.26
    æĺİæĺİ
    -0.26
    å°¼äºļ
    -0.25
    POSITIVE LOGITS
    æĦŁ
    0.37
     molecule
    0.29
    val
    0.29
    cono
    0.28
    èĽĭ
    0.28
    $__
    0.27
    主ä¹īèĢħ
    0.27
    _val
    0.26
    Val
    0.26
    dì
    0.26
    Activations Density 0.025%

    No Known Activations