Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 35989
    Prev
    Next
    INDEX
    Explanations

    specific topics

    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
    作者所有
    -0.08
    审议
    -0.07
     domin
    -0.07
    字第
    -0.07
    ปกครอง
    -0.07
    者が
    -0.07
    арь
    -0.07
     машин
    -0.07
     района
    -0.06
    אוכל
    -0.06
    POSITIVE LOGITS
     Pro
    0.07
    两项
    0.06
     inhibitors
    0.06
     hombres
    0.06
    .drawable
    0.06
    OG
    0.06
     undecided
    0.06
    ܒ
    0.06
    Long
    0.06
     Delegate
    0.06
    Activations Density 0.013%

    No Known Activations