© 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. 75308
    Prev
    Next
    INDEX
    Explanations

    fopen

    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
     "%"
    -0.07
    簋
    -0.06
     JSON
    -0.06
     Forest
    -0.06
     HTTP
    -0.06
     トラック
    -0.06
    ется
    -0.06
     Taken
    -0.06
    _E
    -0.06
    ﮱ
    -0.06
    POSITIVE LOGITS
    neys
    0.07
    	fwrite
    0.07
     fwrite
    0.07
    lu
    0.07
    📈
    0.07
    睦
    0.07
    病因
    0.07
    -reviewed
    0.07
    alem
    0.07
    ahl
    0.07
    Activations Density 0.001%

    No Known Activations