© 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. 76520
    Prev
    Next
    INDEX
    Explanations

    ''

    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
    Accessibility
    -0.08
    gratis
    -0.07
     الكبرى
    -0.07
    asi
    -0.07
     Vs
    -0.07
     mosque
    -0.07
     ,
    -0.07
     ,"
    -0.07
    س
    -0.07
    _epi
    -0.07
    POSITIVE LOGITS
    器械
    0.07
    Metric
    0.07
    台湾
    0.07
    均为
    0.07
    صف
    0.06
    沈阳
    0.06
     ZERO
    0.06
    (Output
    0.06
    绳
    0.06
     unequal
    0.06
    Activations Density 0.000%

    No Known Activations