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. 2842
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    츰
    -0.07
    تأسي
    -0.07
    .GetResponse
    -0.07
    𝕕
    -0.07
    ꦭ
    -0.07
    clus
    -0.07
    同盟
    -0.07
    .Conn
    -0.07
    _Test
    -0.07
    stellen
    -0.07
    POSITIVE LOGITS
     저희
    0.07
     resent
    0.07
    ˲
    0.06
    졍
    0.06
    ග
    0.06
     acknowledge
    0.06
    側
    0.06
    ^.
    0.06
     challenge
    0.06
     adjusting
    0.06
    Activations Density 0.001%

    No Known Activations