© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 2034
    Prev
    Next
    INDEX
    Explanations

    simulate

    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
     Key
    -0.07
     bypass
    -0.07
    ki
    -0.07
    oon
    -0.07
    няя
    -0.07
     Plastic
    -0.07
    (payload
    -0.07
    WWW
    -0.07
    middle
    -0.07
    STATIC
    -0.07
    POSITIVE LOGITS
     ballpark
    0.07
    企业发展
    0.07
    _published
    0.07
    猶
    0.07
     eventName
    0.07
     beast
    0.07
    伊斯兰
    0.07
     сост
    0.07
    FilterWhere
    0.07
    ᐧ
    0.07
    Activations Density 0.010%

    No Known Activations