© 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. 8588
    Prev
    Next
    INDEX
    Explanations

    as

    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
    road
    -0.28
     road
    -0.28
    roads
    -0.26
    管çIJĨéĥ¨éŨ
    -0.26
    çĶ³
    -0.25
    ophobic
    -0.25
    æĴij
    -0.25
    ophobia
    -0.25
    å·¥åķĨå±Ģ
    -0.25
    ismatic
    -0.24
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.30
     rather
    0.28
     sends
    0.27
    èĥĮçĿĢ
    0.26
    èĢĮéĿŀ
    0.26
     calculates
    0.26
     Rather
    0.25
    íĭĢ
    0.25
    æ±ł
    0.25
    andidate
    0.24
    Activations Density 0.003%

    No Known Activations