Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130511
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "../
    -0.08
     Columbus
    -0.07
    iences
    -0.07
    腯
    -0.06
    懦
    -0.06
    不克不及
    -0.06
    was
    -0.06
    -de
    -0.06
    Complex
    -0.06
    出资
    -0.06
    POSITIVE LOGITS
    _IRQ
    0.09
     slows
    0.08
    (mark
    0.07
    TAB
    0.07
    _COUNT
    0.07
     snap
    0.07
     toilets
    0.07
    ynchronize
    0.07
    动人
    0.07
    (binding
    0.07
    Activations Density 0.004%

    No Known Activations