© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5138
    Prev
    Next
    INDEX
    Explanations

    Inc

    np_max-act-logits · gemini-2.0-flash
    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
    esser
    -0.07
    ße
    -0.07
    叨
    -0.07
     Dok
    -0.07
     motion
    -0.07
    venir
    -0.07
    玭
    -0.07
    غضب
    -0.07
     Cec
    -0.07
     shaft
    -0.07
    POSITIVE LOGITS
     neighbouring
    0.08
    _python
    0.07
    identity
    0.07
     LoggerFactory
    0.07
    _feed
    0.07
    _checkpoint
    0.07
    formula
    0.07
     لتحقيق
    0.07
    _root
    0.07
    >(&
    0.07
    Activations Density 0.000%

    No Known Activations