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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129867
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     clarity
    -0.08
    越是
    -0.08
    AlmostEqual
    -0.07
    <(),
    -0.07
     ноя
    -0.07
    anchors
    -0.06
    .Chrome
    -0.06
    .SuspendLayout
    -0.06
    意思是
    -0.06
     أما
    -0.06
    POSITIVE LOGITS
     greens
    0.08
     POP
    0.07
    健康成长
    0.07
     Essentials
    0.07
    _SETTINGS
    0.07
     Huntington
    0.07
    杉
    0.07
    GET
    0.07
     Jews
    0.07
     synthetic
    0.07
    Activations Density 0.069%

    No Known Activations