© 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. 32-TRANSCODER-HP
    7. 41252
    Prev
    Next
    INDEX
    Explanations

    linguistic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.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¯Ńè¨Ģ
    -0.30
     Fé
    -0.28
     speaks
    -0.27
    æ¤Ĵ
    -0.27
    Ec
    -0.27
     Language
    -0.26
    åĿļæŀľ
    -0.25
     language
    -0.24
    èªŀè¨Ģ
    -0.24
    Measured
    -0.24
    POSITIVE LOGITS
    rios
    0.30
     uniforms
    0.30
     nic
    0.29
    atic
    0.27
    genic
    0.26
    uario
    0.26
    LY
    0.26
    aria
    0.25
    å¹²éĥ¨éĺŁä¼į
    0.24
    io
    0.24
    Activations Density 0.001%

    No Known Activations