INDEX

Explanations

the more

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

ards

-0.27

igu

-0.26

pute

-0.26

dling

-0.25

inspace

-0.25

ownt

-0.25

arden

-0.25

 bufio

-0.25

æľķ

-0.24

!='

-0.24

POSITIVE LOGITS

ocre

0.27

 healed

0.26

asing

0.26

ores

0.25

ChildIndex

0.24

ë²Į

0.24

åº·å¤į

0.24

çĽ®çļĦ

0.23

ye

0.23

Psy

0.23

Activations Density 0.001%

the more

No Comments

No Known Activations