© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 69387
    Prev
    Next
    INDEX
    Explanations

    Code/programming errors

    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
     הטבע
    -0.07
     VIN
    -0.07
     Müd
    -0.07
    .var
    -0.07
     va
    -0.07
    莘
    -0.07
     clo
    -0.07
     GLint
    -0.07
     démarche
    -0.07
    _PED
    -0.06
    POSITIVE LOGITS
    sheet
    0.08
    Streamer
    0.08
     Gauge
    0.08
     digest
    0.08
    船
    0.07
    bm
    0.07
    _normalized
    0.07
    殿
    0.07
     stabilization
    0.07
     transformers
    0.07
    Activations Density 0.200%

    No Known Activations