INDEX

Explanations

University

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

ULT

-0.30

ups

-0.29

ivals

-0.28

clamation

-0.27

inations

-0.26

æĺĬ

-0.26

_enabled

-0.26

ÐµÐ¶

-0.25

vironment

-0.25

forth

-0.25

POSITIVE LOGITS

åķĨ

0.30

alloc

0.28

rogate

0.26

 buffers

0.26

ossa

0.25

ä¹ĭäºº

0.25

//'

0.24

ç²½åŃĲ

0.24

èĩŃ

0.24

è¯´æĺİ

0.23

Activations Density 0.001%

University

No Comments

No Known Activations