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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 109353
    Prev
    Next
    INDEX
    Explanations

    9

    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
    咸阳
    -0.08
    Jur
    -0.08
     pylint
    -0.07
     antiqu
    -0.07
    leh
    -0.07
    -di
    -0.07
     employees
    -0.06
    <x
    -0.06
     pok
    -0.06
    -liter
    -0.06
    POSITIVE LOGITS
    ASN
    0.07
     Transparency
    0.07
    MLElement
    0.07
     הש
    0.07
    武侠
    0.07
    =".$_
    0.07
    cząc
    0.07
    assignments
    0.06
    .$
    0.06
    したこと
    0.06
    Activations Density 0.014%

    No Known Activations