INDEX

Explanations

to

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

ean

-0.26

 stakes

-0.25

 dynasty

-0.24

Ĭ

-0.24

 Ð·Ð´Ð¾ÑĢÐ¾Ð²

-0.24

gado

-0.24

 probabilities

-0.24

OSE

-0.24

 machine

-0.24

Wo

-0.24

POSITIVE LOGITS

çŁ

0.27

 normalization

0.26

eration

0.26

liner

0.25

æ¡Ī

0.25

irror

0.25

ded

0.24

çĪ±åĽ½ä¸»ä¹ī

0.24

jspx

0.23

.rep

0.23

Activations Density 0.003%

to

No Comments

No Known Activations