© 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. 23-TRANSCODER-HP
    7. 23918
    Prev
    Next
    INDEX
    Explanations

    Directness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "::
    -0.31
    Ill
    -0.27
    åĬ£
    -0.25
    Behaviour
    -0.25
    ipur
    -0.25
     Behaviour
    -0.24
    erte
    -0.24
     PUB
    -0.24
     Rates
    -0.24
    Å¡t
    -0.23
    POSITIVE LOGITS
    s
    0.36
    ly
    0.33
     technically
    0.29
     linear
    0.28
     technical
    0.28
     intermediate
    0.28
    ness
    0.27
     end
    0.27
     leading
    0.27
     hyp
    0.26
    Activations Density 0.079%

    No Known Activations