© 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. 11-RESID-POST-AA
    6. 69050
    Prev
    Next
    INDEX
    Explanations

    immediately

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otics
    -0.08
    CHK
    -0.07
     ith
    -0.07
    Theme
    -0.07
    TEMPLATE
    -0.07
    建筑业
    -0.07
    𝒸
    -0.07
    IsValid
    -0.06
    .xlabel
    -0.06
    (Fl
    -0.06
    POSITIVE LOGITS
    ritical
    0.08
     greeted
    0.08
     Obama
    0.08
     conced
    0.08
    feito
    0.08
     aprend
    0.07
     distracted
    0.07
    ognition
    0.07
     Reuters
    0.07
    າ
    0.07
    Activations Density 0.007%

    No Known Activations