INDEX

Explanations

by

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

lok

-0.27

èĩªæľī

-0.26

dziaÅĤ

-0.25

 basal

-0.24

ãĥ¼ãĥ³

-0.24

 setting

-0.24

ith

-0.23

pH

-0.23

 Demp

-0.23

 situ

-0.23

POSITIVE LOGITS

clud

0.29

<![

0.29

orca

0.28

åİ»åĵªéĩĮ

0.28

çļĦç¡®

0.27

æ¸Ĳ

0.26

sel

0.26

à¹Ħà¸«à¸§

0.25

åĢ¼å¾Ĺ

0.25

 challeng

0.24

Activations Density 0.001%

by

No Comments

No Known Activations