INDEX

Explanations

reasons

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

reten

-0.26

osal

-0.26

 undert

-0.25

 inade

-0.25

osa

-0.25

éĹ¨å¤ĸ

-0.25

ç±³

-0.24

 inadequate

-0.24

asper

-0.24

Patterns

-0.24

POSITIVE LOGITS

kho

0.27

æ±Ĳ

0.25

Ð³Ð¸Ð½

0.25

urette

0.24

èµ¶

0.24

ä¸¤å²¸

0.23

çīĪ

0.23

↵                        ↵

0.23

_paint

0.23

STYPE

0.23

Activations Density 0.008%

reasons

No Comments

No Known Activations