© 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
    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. 75712
    Prev
    Next
    INDEX
    Explanations

    names

    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
    _tax
    -0.07
     Krishna
    -0.07
    .pow
    -0.07
     DDS
    -0.07
    克里斯
    -0.07
    BALL
    -0.06
    槿
    -0.06
    (',',
    -0.06
     seaw
    -0.06
     CELL
    -0.06
    POSITIVE LOGITS
    jn
    0.07
    труд
    0.07
    odic
    0.07
     introdu
    0.07
     Jane
    0.07
    小さ
    0.07
    dar
    0.07
     Byte
    0.07
    dd
    0.07
    ดา
    0.07
    Activations Density 0.018%

    No Known Activations