© 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. 19-RESID-POST-AA
    11. 70613
    Prev
    Next
    INDEX
    Explanations

    the/in

    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
    abinet
    -0.07
    ential
    -0.07
     pesticides
    -0.07
     trứng
    -0.07
     responds
    -0.07
     '__
    -0.07
     physically
    -0.07
     "__
    -0.06
    ='#
    -0.06
    	glVertex
    -0.06
    POSITIVE LOGITS
    WA
    0.07
    比特币
    0.07
    演变
    0.07
    历史上
    0.07
    _SPLIT
    0.07
     нашей
    0.07
    _Common
    0.07
    _ALIGNMENT
    0.07
    _prepare
    0.07
     THE
    0.06
    Activations Density 0.003%

    No Known Activations