© 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. 70663
    Prev
    Next
    INDEX
    Explanations

    Overcoming problems

    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
    原始
    -0.07
    ested
    -0.07
    𝕮
    -0.07
    atos
    -0.07
    餍
    -0.06
    itating
    -0.06
     citations
    -0.06
     Fitz
    -0.06
    𐌸
    -0.06
    adic
    -0.06
    POSITIVE LOGITS
     imaginary
    0.08
     cover
    0.08
    _EXTENSIONS
    0.07
     Spreadsheet
    0.07
    	sf
    0.07
    $error
    0.07
    董事长
    0.07
     condolences
    0.07
    ``
    0.06
     cohesion
    0.06
    Activations Density 0.002%

    No Known Activations