© 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. 35-TRANSCODER-HP
    7. 39786
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°ĥåīĤ
    -0.26
    ä¸į对
    -0.25
    家åºŃ
    -0.25
    åĨ²åĩ»
    -0.24
    æĭĸ
    -0.24
     instead
    -0.24
    没åħ³ç³»
    -0.24
    åĽ°æī°
    -0.24
    éļĶå£ģ
    -0.23
    è§Ĥ
    -0.23
    POSITIVE LOGITS
    atos
    0.37
    ato
    0.32
    olia
    0.32
    atum
    0.31
    ates
    0.31
    umerator
    0.30
    r
    0.29
    low
    0.29
    uum
    0.29
    atures
    0.29
    Activations Density 0.017%

    No Known Activations