INDEX

Explanations

Variations of "deny"

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

ted

-0.32

ters

-0.27

anager

-0.25

licity

-0.25

 hend

-0.24

 Fortress

-0.24

tes

-0.23

 poder

-0.23

åıĤ

-0.23

None

-0.23

POSITIVE LOGITS

bee

0.25

omi

0.24

iel

0.24

uses

0.23

èĽĽ

0.23

èĢĮçİ°åľ¨

0.23

-automatic

0.23

éĨį

0.23

UTO

0.22

èĢ§

0.22

Activations Density 1.255%

Variations of "deny"

No Comments

No Known Activations