INDEX

Explanations

identification and references

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸĹ

-0.27

è¦ģç´ł

-0.26

olley

-0.26

ãĤıãģĭãĤĬ

-0.25

ÙĪØªØ±

-0.25

çīĻ

-0.25

ä¸īä½į

-0.24

Laugh

-0.23

 Clarence

-0.23

ä¸īç»´

-0.23

POSITIVE LOGITS

ikan

0.29

åµ¬

0.25

step

0.24

 treatment

0.24

-ste

0.24

æºī

0.24

å°ģ

0.24

 Administration

0.24

æĭ¶

0.24

ä¹łè¿ĳ

0.24

Activations Density 0.002%

identification and references

No Comments

No Known Activations