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. 109762
    Prev
    Next
    INDEX
    Explanations

    book

    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
     etree
    -0.07
     incapac
    -0.07
     wt
    -0.07
    Mate
    -0.07
    %=
    -0.07
     peuvent
    -0.07
    suppress
    -0.07
    พระราช
    -0.07
    压制
    -0.07
     doivent
    -0.07
    POSITIVE LOGITS
    ѐ
    0.08
    ǫ
    0.08
    .her
    0.07
    ين
    0.07
    iju
    0.07
    銀
    0.07
    toContain
    0.07
    侬
    0.07
     contracts
    0.07
    	us
    0.07
    Activations Density 0.034%

    No Known Activations