INDEX

Explanations

table

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

Ĳ

-0.29

ï¬Ħ

-0.28

HEME

-0.27

åĲĦæł·

-0.27

è¿ģç§»

-0.27

å¹²åĩĢ

-0.26

ç¼Ł

-0.26

ä¸įæŃ»

-0.26

ç»ĵåĲĪ

-0.25

.delivery

-0.24

POSITIVE LOGITS

çļĦç»ıåħ¸

0.28

orum

0.27

cup

0.27

åĽłä¸ºä»ĸ

0.26

onas

0.25

cup

0.25

 errorCallback

0.25

æĪĳå¿ĥéĩĮ

0.25

çļĦçĶ·äºº

0.25

ci

0.24

Activations Density 0.018%

table

No Comments

No Known Activations