© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 49670
    Prev
    Next
    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repos
    -0.08
    听
    -0.07
     excavation
    -0.07
    DMA
    -0.07
     ADC
    -0.07
    _call
    -0.07
     setTime
    -0.07
    -tested
    -0.07
    _SIGN
    -0.07
    _gas
    -0.07
    POSITIVE LOGITS
    ist
    0.08
    标语
    0.08
    しい
    0.07
     specialist
    0.07
    とは
    0.07
    란
    0.07
    .’
    0.07
     elementType
    0.07
    ］
    0.07
     lĩnh
    0.07
    Activations Density 0.053%

    No Known Activations