© 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. 15-RESID-POST-AA
    11. 5156
    Prev
    Next
    INDEX
    Explanations

    kinetic

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ValidationResult
    -0.07
    🇱
    -0.07
    ],↵↵
    -0.07
    同胞
    -0.06
    อำนวยความสะดวก
    -0.06
     conducts
    -0.06
     우
    -0.06
    },↵↵
    -0.06
     famil
    -0.06
    setCellValue
    -0.06
    POSITIVE LOGITS
    Wire
    0.07
    (ca
    0.07
    rze
    0.07
    -force
    0.07
    したい
    0.07
    .io
    0.07
    十九大
    0.07
    .dump
    0.06
    体现
    0.06
    кая
    0.06
    Activations Density 0.006%

    No Known Activations