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. 23-RESID-POST-AA
    6. 130598
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMPL
    -0.07
    drawer
    -0.07
     [_
    -0.06
    חלב
    -0.06
    高三
    -0.06
    腐败
    -0.06
    벱
    -0.06
    客户的
    -0.06
    ilit
    -0.06
     entreprene
    -0.06
    POSITIVE LOGITS
     quieter
    0.09
     sight
    0.07
    -update
    0.07
    أش
    0.07
     PRODUCT
    0.06
    SEC
    0.06
    อด
    0.06
    Seeing
    0.06
    芷
    0.06
     없
    0.06
    Activations Density 0.019%

    No Known Activations