© 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. 1204
    Prev
    Next
    INDEX
    Explanations

    following

    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
     queryset
    -0.09
    accum
    -0.08
     miesię
    -0.08
    桌上
    -0.07
    phabet
    -0.07
    饲
    -0.07
    🏟
    -0.07
    あれ
    -0.07
    zent
    -0.07
    忮
    -0.07
    POSITIVE LOGITS
     Ma
    0.07
     involving
    0.07
    /$
    0.07
    imson
    0.07
    $s
    0.07
     خاصة
    0.07
    对于
    0.07
    riz
    0.07
    ⋅
    0.07
     instability
    0.07
    Activations Density 0.001%

    No Known Activations