INDEX

Explanations

negation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¹Łä¸įåı¯èĥ½

-0.29

çĽ´éĶĢ

-0.28

lessly

-0.28

åħīçĶµ

-0.25

OPTIONS

-0.25

eneg

-0.25

tÃ³rio

-0.24

enic

-0.24

vrier

-0.24

KeyName

-0.24

POSITIVE LOGITS

ÐµÐºÑĤÐ¾ÑĢ

0.25

èĢĮä¸įæĺ¯

0.24

then

0.24

 Corpor

0.24

 then

0.24

å¡ŀ

0.24

ä¼´

0.24

UMAN

0.24

æ¡ĥ

0.24

ues

0.24

Activations Density 0.002%

negation

No Comments

No Known Activations