INDEX

Explanations

programming code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stack

-0.27

aland

-0.27

oblin

-0.27

lege

-0.25

ilda

-0.24

 Capitals

-0.24

OND

-0.23

_STACK

-0.23

 analyzes

-0.23

_stack

-0.23

POSITIVE LOGITS

 progress

0.26

é¸¦

0.26

apa

0.26

çĽ¸æ¯Ķ

0.26

 performance

0.26

performance

0.25

ä¸įåĥı

0.25

ç©¿

0.25

çº¯åĩĢ

0.24

fas

0.24

Activations Density 0.123%

programming code

No Comments

No Known Activations