INDEX

Explanations

Code and forum posts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arna

-0.29

ahn

-0.27

 rake

-0.26

ban

-0.25

æĩĭ

-0.25

DOC

-0.25

ANE

-0.25

 drag

-0.25

angkan

-0.25

witter

-0.25

POSITIVE LOGITS

id

0.26

TRS

0.26

above

0.24

çŃĶåį·

0.24

 Tune

0.24

 loads

0.24

 above

0.24

 heaps

0.24

ium

0.24

aton

0.24

Activations Density 0.001%

Code and forum posts

No Comments

No Known Activations