© 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. 22-TRANSCODER-HP
    7. 98317
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dia
    -0.26
    inks
    -0.26
    SSF
    -0.24
    mere
    -0.24
    å¾ĹåĪ°äºĨ
    -0.23
     demonstr
    -0.23
    esus
    -0.23
    WISE
    -0.23
    der
    -0.23
     aff
    -0.23
    POSITIVE LOGITS
    icap
    0.28
    åįļ彩
    0.26
     Oriental
    0.26
    ossier
    0.26
     Trophy
    0.25
    ä¼ļç»Ļ
    0.24
    éŀŃ
    0.24
    arius
    0.24
    ropol
    0.24
    reno
    0.23
    Activations Density 0.007%

    No Known Activations