INDEX

Explanations

slope

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 susp

-0.30

ovel

-0.28

éĢ

-0.27

æ²īæ·Ģ

-0.26

rpm

-0.25

åĬĽ

-0.25

 adjustable

-0.25

 Direction

-0.25

èĲ½

-0.25

alah

-0.25

POSITIVE LOGITS

liÄŁ

0.28

 lith

0.28

liÄŁin

0.27

hÃ¤

0.26

_outline

0.25

-limit

0.25

 Lith

0.25

 ÅŁek

0.25

stÃ¤nd

0.24

AuthProvider

0.24

Activations Density 0.250%

slope

No Comments

No Known Activations