INDEX

Explanations

product specifications and measurements

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

çĽ´å¾Ħ

-0.27

punk

-0.27

éĿ¢ç§¯çº¦

-0.26

igrated

-0.25

Dimensions

-0.25

 slab

-0.25

èĢģé¾Ħ

-0.25

oll

-0.24

.refs

-0.24

oki

-0.24

POSITIVE LOGITS

CTL

0.31

ä½ıäºĨ

0.30

 lxml

0.26

acent

0.26

RuntimeObject

0.25

èŁ²

0.25

Ð°Ð½Ð¸

0.24

é¸±

0.23

INI

0.23

 initData

0.23

Activations Density 0.014%

product specifications and measurements

No Comments

No Known Activations