© 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. 98047
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
    Fuse
    -0.27
     Bund
    -0.26
    Attempt
    -0.26
     lacked
    -0.26
    _pm
    -0.25
    å¹´åĪĿ
    -0.24
    capt
    -0.24
    undles
    -0.24
     Regarding
    -0.23
    ughters
    -0.23
    POSITIVE LOGITS
    å¤įæĿĤ
    0.31
    å¤įæĿĤçļĦ
    0.28
     person
    0.27
    åıįæŃ£
    0.27
    roc
    0.26
    å·²
    0.26
    常è§ģ
    0.26
    amil
    0.26
    çĶµåŃIJ
    0.26
    iscal
    0.25
    Activations Density 0.018%

    No Known Activations