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. 15-RESID-POST-AA
    6. 60411
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    티
    -0.09
     Biological
    -0.08
    [Test
    -0.07
     compte
    -0.07
     Pos
    -0.07
    Nic
    -0.07
    _trial
    -0.07
     Radio
    -0.07
    麇
    -0.07
    ,ch
    -0.07
    POSITIVE LOGITS
    קורא
    0.07
    僔
    0.07
     Genç
    0.06
    阅读全文
    0.06
     creeping
    0.06
     marca
    0.06
    гор
    0.06
     garments
    0.06
    곳
    0.06
     SR
    0.06
    Activations Density 0.010%

    No Known Activations