INDEX

Explanations

or

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

æľīæĦıæĢĿ

-0.27

çļĤ

-0.27

tour

-0.25

duck

-0.25

 Wilderness

-0.25

byname

-0.24

çıŃè½¦

-0.24

æµ®

-0.24

Wax

-0.24

//[

-0.24

POSITIVE LOGITS

beck

0.28

ç¾İ

0.27

haft

0.26

åĨįä¹Łä¸į

0.25

EXPECT

0.25

ä¸¾è¡ĮçļĦ

0.25

:numel

0.25

Ð½ÑģÑĤÑĢÑĥ

0.24

opot

0.24

æ¯ĶåĪĨ

0.24

Activations Density 0.427%

or

No Comments

No Known Activations