INDEX

Explanations

Eric

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illing

-0.28

 Ventura

-0.27

ÑĥÐ³

-0.26

 determin

-0.26

ctors

-0.26

ental

-0.25

 cellular

-0.24

 fortune

-0.24

stellung

-0.24

kon

-0.24

POSITIVE LOGITS

 Fixed

0.29

hooks

0.28

host

0.27

éĻĲ

0.27

 pipelines

0.26

Fixed

0.26

.pipe

0.26

Lim

0.25

Lim

0.25

.Interop

0.25

Activations Density 0.008%

Eric

No Comments

No Known Activations