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. 130065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    파
    -0.07
    أسباب
    -0.07
     amacıyla
    -0.07
     Stef
    -0.07
    nehmer
    -0.06
     labelText
    -0.06
    ם
    -0.06
    黻
    -0.06
    doğan
    -0.06
    amt
    -0.06
    POSITIVE LOGITS
    peech
    0.07
    URRENT
    0.07
     bands
    0.07
     код
    0.07
    SUB
    0.07
     stripping
    0.07
    ancellation
    0.07
    _DAYS
    0.06
    .Client
    0.06
    一个小
    0.06
    Activations Density 0.014%

    No Known Activations