Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129927
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    썻
    -0.07
    Unfortunately
    -0.06
     lied
    -0.06
     Ort
    -0.06
    Cancel
    -0.06
    [axis
    -0.06
    စ
    -0.06
    .contract
    -0.06
    \Action
    -0.06
    ")->
    -0.06
    POSITIVE LOGITS
     NE
    0.07
    กระจ
    0.07
    Office
    0.07
     Nẵng
    0.07
    띵
    0.06
    使用網路
    0.06
    'Re
    0.06
    눙
    0.06
     NAND
    0.06
    נדר
    0.06
    Activations Density 0.001%

    No Known Activations