INDEX

Explanations

freshwater

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

èĢĥåľº

-0.30

valuator

-0.28

Lorem

-0.27

çĶĳ

-0.27

ä»İåİ»å¹´

-0.26

_roi

-0.24

.constructor

-0.24

è·ĳäºĨ

-0.24

tha

-0.24

 Lockheed

-0.23

POSITIVE LOGITS

Below

0.30

 Below

0.29

sno

0.28

omens

0.28

 diagram

0.26

Ð¸ÑĢÐ¾Ð²ÐºÐ¸

0.25

_ten

0.25

ities

0.24

holds

0.24

iset

0.24

Activations Density 0.002%

freshwater

No Comments

No Known Activations