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. 44166
    Prev
    Next
    INDEX
    Explanations

    is

    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
    lace
    -0.07
    mirror
    -0.07
    慈悲
    -0.07
    اعتم
    -0.07
    𝓈
    -0.07
    ทำความ
    -0.07
    𨱏
    -0.07
    ꦫ
    -0.07
    ,type
    -0.07
    incinn
    -0.07
    POSITIVE LOGITS
    遒
    0.08
     undis
    0.08
    _pr
    0.07
     less
    0.07
    的信心
    0.07
    _unlock
    0.07
     Divider
    0.07
     protester
    0.07
     وج
    0.07
    (ent
    0.07
    Activations Density 0.002%

    No Known Activations