INDEX

Explanations

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 icon

-0.27

.usage

-0.25

 empres

-0.25

 usage

-0.25

tab

-0.24

usage

-0.24

mma

-0.24

ISTA

-0.24

spr

-0.24

Microsoft

-0.23

POSITIVE LOGITS

ä¸Ńæŀ¢

0.28

ÑĨÐµ

0.28

å¤§èĦĳ

0.27

èĤłèĥĥ

0.27

pus

0.26

-Jul

0.26

è¤Ĭ

0.25

cale

0.25

keh

0.24

 sluggish

0.24

Activations Density 0.008%

the

No Comments

No Known Activations