INDEX

Explanations

programming code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

inc

-0.28

ocup

-0.26

SES

-0.25

meter

-0.25

ISM

-0.25

 ourselves

-0.24

Ses

-0.24

ìĬ¤íĥĢ

-0.24

 evolve

-0.24

 regime

-0.24

POSITIVE LOGITS

<*

0.26

.Payload

0.26

amburger

0.25

DOG

0.25

)(*

0.25

plash

0.24

 bootstrap

0.24

æĤ²åī§

0.24

anuts

0.24

[*

0.24

Activations Density 0.021%

programming code

No Comments

No Known Activations