INDEX

Explanations

academic research

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

hey

-0.25

 Reserve

-0.25

å¡ŀ

-0.25

ley

-0.24

 Motors

-0.23

leness

-0.23

 Pistons

-0.23

 Purpose

-0.23

 reserve

-0.23

Pil

-0.23

POSITIVE LOGITS

CHASE

0.33

 Souls

0.26

åİĨåı²

0.26

 results

0.26

KD

0.25

 Bett

0.25

xC

0.25

CTOR

0.24

agger

0.24

DTD

0.24

Activations Density 0.001%

academic research

No Comments

No Known Activations