Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 129582
    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
    耻
    -0.08
     melhores
    -0.07
     Ax
    -0.07
    ournal
    -0.07
     Addiction
    -0.07
     swimming
    -0.07
    نفس
    -0.07
     rocks
    -0.07
     aluno
    -0.07
     Axel
    -0.06
    POSITIVE LOGITS
    基调
    0.07
    With
    0.07
    ┬
    0.07
    _compiler
    0.06
     "'.
    0.06
    /key
    0.06
    (panel
    0.06
     pobli
    0.06
    Holy
    0.06
    _mirror
    0.06
    Activations Density 0.001%

    No Known Activations