© 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. 23-RESID-POST-AA
    11. 925
    Prev
    Next
    INDEX
    Explanations

    code, data, files

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    땋
    -0.08
    𝕐
    -0.07
    "title
    -0.07
    .Enter
    -0.07
    섀
    -0.07
    'hui
    -0.07
    .integer
    -0.07
    (image
    -0.07
    itag
    -0.07
     chief
    -0.06
    POSITIVE LOGITS
     circum
    0.07
    prec
    0.07
     Elev
    0.07
    ↵            
↵
    0.07
    Hooks
    0.06
     AW
    0.06
    _fence
    0.06
    /cc
    0.06
     ↵            ↵
    0.06
     Main
    0.06
    Activations Density 0.040%

    No Known Activations