© 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 EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 81130
    Prev
    Next
    INDEX
    Explanations

    ")

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.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
     Optical
    -0.07
    ༔
    -0.07
    נסה
    -0.07
    PART
    -0.07
    _nome
    -0.07
    开发建设
    -0.07
    Virtual
    -0.07
     JSX
    -0.07
     setup
    -0.07
    POSITIVE LOGITS
    �
    0.07
    bower
    0.07
    BS
    0.07
     cues
    0.07
     jig
    0.06
    ired
    0.06
    DIG
    0.06
     earrings
    0.06
    _frames
    0.06
     floated
    0.06
    Activations Density 0.111%

    No Known Activations