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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 128626
    Prev
    Next
    INDEX
    Explanations

    Cultural properties/monuments

    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
    -day
    -0.07
    之前的
    -0.07
    ovation
    -0.07
    EMBER
    -0.07
     Extension
    -0.07
    	sum
    -0.07
     Manny
    -0.07
     charming
    -0.07
     SetUp
    -0.06
     Items
    -0.06
    POSITIVE LOGITS
     urgency
    0.07
    ԝ
    0.07
    溱
    0.07
    /ioutil
    0.07
     Locate
    0.07
     NSMutableArray
    0.07
    我又
    0.06
    뱋
    0.06
    OLEAN
    0.06
     Else
    0.06
    Activations Density 0.037%

    No Known Activations