© 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. 15-RESID-POST-AA
    11. 30539
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    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
     rename
    -0.07
     представ
    -0.07
     hass
    -0.07
    stdbool
    -0.07
    (train
    -0.07
    מכון
    -0.07
     Unterstüt
    -0.06
     Find
    -0.06
    	struct
    -0.06
    _PROM
    -0.06
    POSITIVE LOGITS
    atical
    0.07
    Bracket
    0.07
     cultivation
    0.07
    queen
    0.07
     canyon
    0.07
    峂
    0.07
    _hor
    0.06
    邽
    0.06
    illow
    0.06
    _keyword
    0.06
    Activations Density 0.001%

    No Known Activations